> ## Documentation Index > Fetch the complete documentation index at: https://gladia-95-jl-ml-93-amd-docs-clean.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Live WebSocket > WebSocket to send audio chunks and receive events. ## AsyncAPI ````yaml asyncapi.yaml liveTranscription id: liveTranscription title: Live transcription description: Single WebSocket channel for all client->server and server->client messages. servers: - id: real-time protocol: wss host: api.gladia.io/v2/live?token={SESSION} bindings: [] variables: [] address: liveTranscription parameters: [] bindings: [] operations: - &ref_15 id: sendAudioChunkJson title: Send audio chunk json description: Send an audio chunk as JSON (base64). type: receive messages: - &ref_35 id: audioChunkJson contentType: application/json payload: - name: Audio Chunk (JSON) description: Send audio bytes as base64-encoded chunk. type: object properties: - name: type type: string description: audio_chunk required: true - name: data type: object required: true properties: - name: chunk type: string description: Base64-encoded raw audio bytes. required: true headers: [] jsonPayloadSchema: type: object required: - type - data properties: type: type: string const: audio_chunk x-parser-schema-id: data: type: object required: - chunk properties: chunk: type: string description: Base64-encoded raw audio bytes. x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: title: Audio Chunk (JSON) description: Send audio bytes as base64-encoded chunk. example: |- { "type": "audio_chunk", "data": { "chunk": "UklGRiQAAABXQVZFZm10IBIAAAABAAEAESsAACJWAAACABAAZGF0YQAAAA==" } } bindings: [] extensions: - id: x-parser-unique-object-id value: audioChunkJson bindings: [] extensions: &ref_0 - id: x-parser-unique-object-id value: liveTranscription - &ref_16 id: sendAudioChunkBinary title: Send audio chunk binary description: Send an audio chunk as a binary frame. type: receive messages: - &ref_36 id: audioChunkBinary contentType: application/octet-stream payload: - type: string format: binary description: Send audio bytes as a binary WebSocket frame. x-parser-schema-id: name: Audio Chunk (Binary frame) headers: [] jsonPayloadSchema: type: string format: binary description: >- Raw audio bytes matching the session encoding/bit_depth/sample_rate/channels. x-parser-schema-id: title: Audio Chunk (Binary frame) description: Send audio bytes as a binary WebSocket frame. example: '{}' bindings: [] extensions: - id: x-parser-unique-object-id value: audioChunkBinary bindings: [] extensions: *ref_0 - &ref_17 id: sendStopRecording title: Send stop recording description: Stop recording. type: receive messages: - &ref_37 id: stopRecording contentType: application/json payload: - name: Stop Recording description: Inform Gladia that recording is over. type: object properties: - name: type type: string description: stop_recording required: true headers: [] jsonPayloadSchema: type: object required: - type properties: type: type: string const: stop_recording x-parser-schema-id: x-parser-schema-id: title: Stop Recording description: Inform Gladia that recording is over. example: |- { "type": "stop_recording" } bindings: [] extensions: - id: x-parser-unique-object-id value: stopRecording bindings: [] extensions: *ref_0 - &ref_18 id: onTranscript title: On transcript type: send messages: - &ref_38 id: transcript contentType: application/json payload: - name: Transcript description: >- This message contains the informations about the transcript of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: &ref_1 - 550e8400-e29b-41d4-a716-446655440000 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: &ref_2 - '2025-09-19T12:34:56Z' required: true - name: type type: string description: transcript required: true - name: data type: object required: true properties: - name: id type: string required: true - name: is_final type: boolean description: Indicates if the transcript is final or partial. required: true - name: utterance type: object description: >- Continuous segment of speech with timing, text and optional channel. examples: &ref_3 - start: 1.02 end: 3.44 confidence: 0.93 channel: 0 words: - word: good start: 1.02 end: 1.21 confidence: 0.96 - word: morning start: 1.22 end: 1.55 confidence: 0.95 text: good morning language: en required: true properties: - name: start type: number description: >- Start time of the utterance in seconds from session start. required: false - name: end type: number description: >- End time of the utterance in seconds from session start. required: false - name: confidence type: number description: Confidence score for the utterance between 0 and 1. required: false - name: channel type: integer description: >- Audio channel index (0-based) if multiple channels are present. required: false - name: words type: array description: Word-level details for this utterance. required: false properties: - name: word type: string description: Recognized token as spoken in the audio. required: false - name: start type: number description: >- Start time of the word in seconds from session start. required: false - name: end type: number description: >- End time of the word in seconds from session start. required: false - name: confidence type: number description: Confidence score for the token between 0 and 1. required: false - name: text type: string description: The transcribed text for the utterance. required: false - name: language type: string description: >- BCP-47 language tag detected for the utterance (e.g. "en"). required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: &ref_4 type: string format: uuid description: UUID identifying the session. examples: *ref_1 x-parser-schema-id: UUID created_at: &ref_5 type: string format: date-time description: ISO 8601 timestamp in UTC. examples: *ref_2 x-parser-schema-id: ISODateTime type: type: string const: transcript x-parser-schema-id: data: type: object required: - id - is_final - utterance properties: id: type: string x-parser-schema-id: is_final: type: boolean description: Indicates if the transcript is final or partial. x-parser-schema-id: utterance: &ref_8 type: object properties: start: type: number description: >- Start time of the utterance in seconds from session start. x-parser-schema-id: end: type: number description: End time of the utterance in seconds from session start. x-parser-schema-id: confidence: type: number description: Confidence score for the utterance between 0 and 1. x-parser-schema-id: channel: type: integer description: >- Audio channel index (0-based) if multiple channels are present. x-parser-schema-id: words: type: array items: &ref_14 type: object properties: word: type: string description: Recognized token as spoken in the audio. x-parser-schema-id: start: type: number description: >- Start time of the word in seconds from session start. x-parser-schema-id: end: type: number description: >- End time of the word in seconds from session start. x-parser-schema-id: confidence: type: number description: Confidence score for the token between 0 and 1. x-parser-schema-id: description: >- Word-level timing and confidence for a token in the transcript. examples: - word: hello start: 0.12 end: 0.38 confidence: 0.97 x-parser-schema-id: Word description: Word-level details for this utterance. x-parser-schema-id: text: type: string description: The transcribed text for the utterance. x-parser-schema-id: language: type: string description: >- BCP-47 language tag detected for the utterance (e.g. "en"). x-parser-schema-id: description: >- Continuous segment of speech with timing, text and optional channel. examples: *ref_3 x-parser-schema-id: Utterance x-parser-schema-id: description: >- Realtime transcript update for an utterance; may be interim or final. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:34:10Z' type: transcript data: id: 00-00000011 is_final: true utterance: start: 0 end: 0.48 confidence: 0.91 channel: 0 words: - word: Hello start: 0 end: 0.35 confidence: 0.91 - word: world start: 0.36 end: 0.48 confidence: 0.91 text: Hello world. language: en x-parser-schema-id: TranscriptMessage title: Transcript description: >- This message contains the informations about the transcript of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:34:10Z", "type": "transcript", "data": { "id": "00-00000011", "is_final": true, "utterance": { "start": 0, "end": 0.48, "confidence": 0.91, "channel": 0, "words": [ { "word": "Hello", "start": 0, "end": 0.35, "confidence": 0.91 }, { "word": "world", "start": 0.36, "end": 0.48, "confidence": 0.91 } ], "text": "Hello world.", "language": "en" } } } bindings: [] extensions: - id: x-parser-unique-object-id value: transcript bindings: [] extensions: *ref_0 - &ref_19 id: onSpeechStart title: On speech start type: send messages: - &ref_39 id: speechStart contentType: application/json payload: - name: Speech Start description: >- Indicates the start of detected speech activity on a given channel. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: type type: string description: speech_start required: true - name: data type: object description: Timing information for speech start/end events. examples: &ref_6 - time: 1.24 channel: 0 required: true properties: - name: time type: number description: >- Time in seconds from session start when the event occurred. required: false - name: channel type: integer description: Audio channel index (0-based) for which the event applies. required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 type: type: string const: speech_start x-parser-schema-id: data: &ref_7 type: object properties: time: type: number description: Time in seconds from session start when the event occurred. x-parser-schema-id: channel: type: integer description: Audio channel index (0-based) for which the event applies. x-parser-schema-id: description: Timing information for speech start/end events. examples: *ref_6 x-parser-schema-id: SpeechEventData description: Indicates the start of detected speech activity on a given channel. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:34:06Z' type: speech_start data: time: 1.24 channel: 0 x-parser-schema-id: SpeechEventMessage title: Speech Start description: Indicates the start of detected speech activity on a given channel. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:34:06Z", "type": "speech_start", "data": { "time": 1.24, "channel": 0 } } bindings: [] extensions: - id: x-parser-unique-object-id value: speechStart bindings: [] extensions: *ref_0 - &ref_20 id: onSpeechEnd title: On speech end type: send messages: - &ref_40 id: speechEnd contentType: application/json payload: - name: Speech End description: Indicates the end of detected speech activity. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: type type: string description: speech_end required: true - name: data type: object description: Timing information for speech start/end events. examples: *ref_6 required: true properties: - name: time type: number description: >- Time in seconds from session start when the event occurred. required: false - name: channel type: integer description: Audio channel index (0-based) for which the event applies. required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 type: type: string const: speech_end x-parser-schema-id: data: *ref_7 description: Indicates the end of detected speech activity. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:34:09Z' type: speech_end data: time: 3.1 channel: 0 x-parser-schema-id: SpeechEventMessageEnd title: Speech End description: Indicates the end of detected speech activity. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:34:09Z", "type": "speech_end", "data": { "time": 3.1, "channel": 0 } } bindings: [] extensions: - id: x-parser-unique-object-id value: speechEnd bindings: [] extensions: *ref_0 - &ref_21 id: onAnsweringMachine title: On answering machine type: send messages: - &ref_41 id: answeringMachine contentType: application/json payload: - name: Answering Machine description: Reports whether a human or an answering machine picked up. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: type type: string description: answering_machine required: true - name: data type: object description: Outcome of answering machine detection for the session. required: true properties: - name: kind type: string description: >- Whether a person picked up or the call reached an answering machine. enumValues: - human - machine required: true - name: confidence type: number description: >- How machine-like the call opening was, between 0 and 1. This is a ranking score, not a calibrated probability: compare it against a threshold tuned on your own traffic rather than reading it as a likelihood. required: true - name: time type: number description: >- Position in the audio stream, in seconds from the start of the session, at which the decision was taken. Measured on the audio timeline and sharing the same reference as speech_start, speech_end and transcript, so all messages can be ordered against each other. Use created_at to correlate with wall-clock logs. required: true - name: channel type: integer description: >- Audio channel index (0-based) for which the decision applies. required: false headers: [] jsonPayloadSchema: title: Answering Machine type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 type: type: string const: answering_machine x-parser-schema-id: data: type: object required: - kind - confidence - time properties: kind: type: string enum: - human - machine description: >- Whether a person picked up or the call reached an answering machine. x-parser-schema-id: confidence: type: number minimum: 0 maximum: 1 description: >- How machine-like the call opening was, between 0 and 1. This is a ranking score, not a calibrated probability: compare it against a threshold tuned on your own traffic rather than reading it as a likelihood. x-parser-schema-id: time: type: number description: >- Position in the audio stream, in seconds from the start of the session, at which the decision was taken. Measured on the audio timeline and sharing the same reference as speech_start, speech_end and transcript, so all messages can be ordered against each other. Use created_at to correlate with wall-clock logs. x-parser-schema-id: channel: type: integer description: >- Audio channel index (0-based) for which the decision applies. x-parser-schema-id: description: Outcome of answering machine detection for the session. x-parser-schema-id: description: >- Reports whether a human or an answering machine picked up. Emitted at most once per session, about five seconds after the first speech, and never revised. Not emitted if nobody speaks or if the session ends before the decision. Does not require transcription, so it behaves the same across languages; partial or final transcripts may arrive before it. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2026-09-09T12:34:11Z' type: answering_machine data: kind: machine confidence: 0.78 time: 5.24 channel: 0 - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2026-09-09T12:34:11Z' type: answering_machine data: kind: human confidence: 0.12 time: 5.31 channel: 0 x-parser-schema-id: AnsweringMachineMessage title: Answering Machine description: Reports whether a human or an answering machine picked up. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2026-09-09T12:34:11Z", "type": "answering_machine", "data": { "kind": "machine", "confidence": 0.78, "time": 5.24, "channel": 0 } } bindings: [] extensions: - id: x-parser-unique-object-id value: answeringMachine bindings: [] extensions: *ref_0 - &ref_22 id: onTranslation title: On translation type: send messages: - &ref_42 id: translation contentType: application/json payload: - name: Translation description: >- This message contains the informations about the translation of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: type type: string description: translation required: true - name: data type: object required: true properties: - name: utterance_id type: string required: true - name: utterance type: object description: >- Continuous segment of speech with timing, text and optional channel. examples: *ref_3 required: true properties: - name: start type: number description: >- Start time of the utterance in seconds from session start. required: false - name: end type: number description: >- End time of the utterance in seconds from session start. required: false - name: confidence type: number description: Confidence score for the utterance between 0 and 1. required: false - name: channel type: integer description: >- Audio channel index (0-based) if multiple channels are present. required: false - name: words type: array description: Word-level details for this utterance. required: false properties: - name: word type: string description: Recognized token as spoken in the audio. required: false - name: start type: number description: >- Start time of the word in seconds from session start. required: false - name: end type: number description: >- End time of the word in seconds from session start. required: false - name: confidence type: number description: Confidence score for the token between 0 and 1. required: false - name: text type: string description: The transcribed text for the utterance. required: false - name: language type: string description: >- BCP-47 language tag detected for the utterance (e.g. "en"). required: false - name: original_language type: string required: true - name: target_language type: string required: true - name: translated_utterance type: object description: >- Continuous segment of speech with timing, text and optional channel. examples: *ref_3 required: true properties: - name: start type: number description: >- Start time of the utterance in seconds from session start. required: false - name: end type: number description: >- End time of the utterance in seconds from session start. required: false - name: confidence type: number description: Confidence score for the utterance between 0 and 1. required: false - name: channel type: integer description: >- Audio channel index (0-based) if multiple channels are present. required: false - name: words type: array description: Word-level details for this utterance. required: false properties: - name: word type: string description: Recognized token as spoken in the audio. required: false - name: start type: number description: >- Start time of the word in seconds from session start. required: false - name: end type: number description: >- End time of the word in seconds from session start. required: false - name: confidence type: number description: Confidence score for the token between 0 and 1. required: false - name: text type: string description: The transcribed text for the utterance. required: false - name: language type: string description: >- BCP-47 language tag detected for the utterance (e.g. "en"). required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 error: oneOf: - type: 'null' x-parser-schema-id: - &ref_9 type: object properties: status_code: oneOf: - type: integer x-parser-schema-id: - type: string x-parser-schema-id: description: HTTP-like code or provider-specific status string. x-parser-schema-id: exception: type: string description: Short machine-readable error name. x-parser-schema-id: message: type: string description: Human-readable error explanation. x-parser-schema-id: description: >- Standard error container included in payloads when an operation fails. examples: - status_code: 400 exception: InvalidArgument message: Unsupported sample rate x-parser-schema-id: ErrorObject x-parser-schema-id: type: type: string const: translation x-parser-schema-id: data: type: object required: - utterance_id - utterance - original_language - target_language - translated_utterance properties: utterance_id: type: string x-parser-schema-id: utterance: *ref_8 original_language: type: string x-parser-schema-id: target_language: type: string x-parser-schema-id: translated_utterance: *ref_8 x-parser-schema-id: description: >- Translation result for an utterance into the requested target language. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:34:20Z' type: translation error: null data: utterance_id: utt_001 utterance: text: buenos días language: es start: 4.2 end: 6.1 original_language: es target_language: en translated_utterance: text: good morning language: en start: 4.2 end: 6.1 x-parser-schema-id: TranslationMessage title: Translation description: >- This message contains the informations about the translation of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:34:20Z", "type": "translation", "error": null, "data": { "utterance_id": "utt_001", "utterance": { "text": "buenos días", "language": "es", "start": 4.2, "end": 6.1 }, "original_language": "es", "target_language": "en", "translated_utterance": { "text": "good morning", "language": "en", "start": 4.2, "end": 6.1 } } } bindings: [] extensions: - id: x-parser-unique-object-id value: translation bindings: [] extensions: *ref_0 - &ref_23 id: onNamedEntityRecognition title: On named entity recognition type: send messages: - &ref_43 id: namedEntityRecognition contentType: application/json payload: - name: Named Entity Recognition description: >- This message contains the informations about the named entity recognition of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: type type: string description: named_entity_recognition required: true - name: data type: object required: true properties: - name: utterance_id type: string required: true - name: utterance type: object description: >- Continuous segment of speech with timing, text and optional channel. examples: *ref_3 required: true properties: - name: start type: number description: >- Start time of the utterance in seconds from session start. required: false - name: end type: number description: >- End time of the utterance in seconds from session start. required: false - name: confidence type: number description: Confidence score for the utterance between 0 and 1. required: false - name: channel type: integer description: >- Audio channel index (0-based) if multiple channels are present. required: false - name: words type: array description: Word-level details for this utterance. required: false properties: - name: word type: string description: Recognized token as spoken in the audio. required: false - name: start type: number description: >- Start time of the word in seconds from session start. required: false - name: end type: number description: >- End time of the word in seconds from session start. required: false - name: confidence type: number description: Confidence score for the token between 0 and 1. required: false - name: text type: string description: The transcribed text for the utterance. required: false - name: language type: string description: >- BCP-47 language tag detected for the utterance (e.g. "en"). required: false - name: results type: array required: true properties: - name: entity_type type: string required: false - name: text type: string required: false - name: start type: number required: false - name: end type: number required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: type: type: string const: named_entity_recognition x-parser-schema-id: data: type: object required: - utterance_id - utterance - results properties: utterance_id: type: string x-parser-schema-id: utterance: *ref_8 results: type: array items: type: object properties: entity_type: type: string x-parser-schema-id: text: type: string x-parser-schema-id: start: type: number x-parser-schema-id: end: type: number x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: description: Named entity recognition results extracted from the given utterance. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:34:30Z' type: named_entity_recognition error: null data: utterance_id: utt_002 utterance: text: meeting with Alice at 3pm start: 7 end: 10.5 results: - entity_type: PERSON text: Alice start: 2 end: 2.5 - entity_type: TIME text: 3pm start: 3 end: 3.3 x-parser-schema-id: NamedEntityRecognitionMessage title: Named Entity Recognition description: >- This message contains the informations about the named entity recognition of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:34:30Z", "type": "named_entity_recognition", "error": null, "data": { "utterance_id": "utt_002", "utterance": { "text": "meeting with Alice at 3pm", "start": 7, "end": 10.5 }, "results": [ { "entity_type": "PERSON", "text": "Alice", "start": 2, "end": 2.5 }, { "entity_type": "TIME", "text": "3pm", "start": 3, "end": 3.3 } ] } } bindings: [] extensions: - id: x-parser-unique-object-id value: namedEntityRecognition bindings: [] extensions: *ref_0 - &ref_24 id: onSentimentAnalysis title: On sentiment analysis type: send messages: - &ref_44 id: sentimentAnalysis contentType: application/json payload: - name: Sentiment Analysis description: >- This message contains the informations about the sentiment analysis of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: type type: string description: sentiment_analysis required: true - name: data type: object required: true properties: - name: utterance_id type: string required: true - name: utterance type: object description: >- Continuous segment of speech with timing, text and optional channel. examples: *ref_3 required: true properties: - name: start type: number description: >- Start time of the utterance in seconds from session start. required: false - name: end type: number description: >- End time of the utterance in seconds from session start. required: false - name: confidence type: number description: Confidence score for the utterance between 0 and 1. required: false - name: channel type: integer description: >- Audio channel index (0-based) if multiple channels are present. required: false - name: words type: array description: Word-level details for this utterance. required: false properties: - name: word type: string description: Recognized token as spoken in the audio. required: false - name: start type: number description: >- Start time of the word in seconds from session start. required: false - name: end type: number description: >- End time of the word in seconds from session start. required: false - name: confidence type: number description: Confidence score for the token between 0 and 1. required: false - name: text type: string description: The transcribed text for the utterance. required: false - name: language type: string description: >- BCP-47 language tag detected for the utterance (e.g. "en"). required: false - name: results type: array required: true properties: - name: sentiment type: string required: false - name: emotion type: string required: false - name: text type: string required: false - name: start type: number required: false - name: end type: number required: false - name: channel type: integer required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: type: type: string const: sentiment_analysis x-parser-schema-id: data: type: object required: - utterance_id - utterance - results properties: utterance_id: type: string x-parser-schema-id: utterance: *ref_8 results: type: array items: type: object properties: sentiment: type: string x-parser-schema-id: emotion: type: string x-parser-schema-id: text: type: string x-parser-schema-id: start: type: number x-parser-schema-id: end: type: number x-parser-schema-id: channel: type: integer x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: description: >- Sentiment and emotion analysis associated with segments of an utterance. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:34:35Z' type: sentiment_analysis error: null data: utterance_id: utt_003 utterance: text: I love this product! start: 11 end: 13.2 results: - sentiment: positive emotion: joy text: love this product start: 11.4 end: 12.9 channel: 0 x-parser-schema-id: SentimentAnalysisMessage title: Sentiment Analysis description: >- This message contains the informations about the sentiment analysis of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:34:35Z", "type": "sentiment_analysis", "error": null, "data": { "utterance_id": "utt_003", "utterance": { "text": "I love this product!", "start": 11, "end": 13.2 }, "results": [ { "sentiment": "positive", "emotion": "joy", "text": "love this product", "start": 11.4, "end": 12.9, "channel": 0 } ] } } bindings: [] extensions: - id: x-parser-unique-object-id value: sentimentAnalysis bindings: [] extensions: *ref_0 - &ref_25 id: onPostTranscript title: On post transcript type: send messages: - &ref_45 id: postTranscript contentType: application/json payload: - name: Post Transcript description: >- This message contains the informations about the post transcript of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: type type: string description: post_transcript required: true - name: data type: object description: >- Aggregated transcription artifacts produced after the session completes. examples: &ref_10 - full_transcript: hello world languages: - en sentences: - success: true is_empty: false exec_time: 0.11 error: null results: - Hello world. subtitles: - format: srt subtitles: | 1 00:00:00,000 --> 00:00:01,000 Hello world utterances: - start: 0 end: 0.9 text: hello world required: true properties: - name: full_transcript type: string required: false - name: languages type: array required: false properties: - name: item type: string required: false - name: sentences type: array required: false properties: - name: success type: boolean required: false - name: is_empty type: boolean required: false - name: exec_time type: number required: false - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: results type: array required: false properties: - name: item type: string required: false - name: subtitles type: array required: false properties: - name: format type: string enumValues: - srt - vtt - ass required: false - name: subtitles type: string required: false - name: utterances type: array required: false properties: - name: start type: number description: >- Start time of the utterance in seconds from session start. required: false - name: end type: number description: >- End time of the utterance in seconds from session start. required: false - name: confidence type: number description: Confidence score for the utterance between 0 and 1. required: false - name: channel type: integer description: >- Audio channel index (0-based) if multiple channels are present. required: false - name: words type: array description: Word-level details for this utterance. required: false properties: - name: word type: string description: Recognized token as spoken in the audio. required: false - name: start type: number description: >- Start time of the word in seconds from session start. required: false - name: end type: number description: >- End time of the word in seconds from session start. required: false - name: confidence type: number description: Confidence score for the token between 0 and 1. required: false - name: text type: string description: The transcribed text for the utterance. required: false - name: language type: string description: >- BCP-47 language tag detected for the utterance (e.g. "en"). required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 type: type: string const: post_transcript x-parser-schema-id: data: &ref_11 type: object properties: full_transcript: type: string x-parser-schema-id: languages: type: array items: type: string x-parser-schema-id: x-parser-schema-id: sentences: type: array items: &ref_12 type: object properties: success: type: boolean x-parser-schema-id: is_empty: type: boolean x-parser-schema-id: exec_time: type: number x-parser-schema-id: error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: results: type: array items: type: string x-parser-schema-id: x-parser-schema-id: description: >- Result container for sentence-level operations such as punctuation or translation. examples: - success: true is_empty: false exec_time: 0.12 error: null results: - Hello, world. x-parser-schema-id: SentenceResult x-parser-schema-id: subtitles: type: array items: &ref_13 type: object properties: format: type: string enum: - srt - vtt - ass x-parser-schema-id: subtitles: type: string x-parser-schema-id: description: Subtitle payload for a specific format. examples: - format: vtt subtitles: | WEBVTT 00:00:00.000 --> 00:00:01.000 Hello world x-parser-schema-id: SubtitleBlock x-parser-schema-id: utterances: type: array items: *ref_8 x-parser-schema-id: description: >- Aggregated transcription artifacts produced after the session completes. examples: *ref_10 x-parser-schema-id: PostTranscriptData description: >- Post-processing transcript payload containing full text and artifacts. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:40:00Z' type: post_transcript data: full_transcript: hello world x-parser-schema-id: PostTranscriptMessage title: Post Transcript description: >- This message contains the informations about the post transcript of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:40:00Z", "type": "post_transcript", "data": { "full_transcript": "hello world" } } bindings: [] extensions: - id: x-parser-unique-object-id value: postTranscript bindings: [] extensions: *ref_0 - &ref_26 id: onPostFinalTranscript title: On post final transcript type: send messages: - &ref_46 id: postFinalTranscript contentType: application/json payload: - name: Final transcript (aggregated) description: >- This message contains the informations about the post final transcript of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: type type: string description: post_final_transcript required: true - name: data type: object required: true properties: - name: metadata type: object required: false properties: - name: audio_duration type: number required: false - name: number_of_distinct_channels type: integer required: false - name: billing_time type: number required: false - name: transcription_time type: number required: false - name: transcription type: object description: >- Aggregated transcription artifacts produced after the session completes. examples: *ref_10 required: false properties: - name: full_transcript type: string required: false - name: languages type: array required: false properties: - name: item type: string required: false - name: sentences type: array required: false properties: - name: success type: boolean required: false - name: is_empty type: boolean required: false - name: exec_time type: number required: false - name: error type: object required: false properties: - name: status_code type: oneOf description: >- HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: results type: array required: false properties: - name: item type: string required: false - name: subtitles type: array required: false properties: - name: format type: string enumValues: - srt - vtt - ass required: false - name: subtitles type: string required: false - name: utterances type: array required: false properties: - name: start type: number description: >- Start time of the utterance in seconds from session start. required: false - name: end type: number description: >- End time of the utterance in seconds from session start. required: false - name: confidence type: number description: >- Confidence score for the utterance between 0 and 1. required: false - name: channel type: integer description: >- Audio channel index (0-based) if multiple channels are present. required: false - name: words type: array description: Word-level details for this utterance. required: false properties: - name: word type: string description: Recognized token as spoken in the audio. required: false - name: start type: number description: >- Start time of the word in seconds from session start. required: false - name: end type: number description: >- End time of the word in seconds from session start. required: false - name: confidence type: number description: >- Confidence score for the token between 0 and 1. required: false - name: text type: string description: The transcribed text for the utterance. required: false - name: language type: string description: >- BCP-47 language tag detected for the utterance (e.g. "en"). required: false - name: translation type: object required: false properties: - name: success type: boolean required: false - name: is_empty type: boolean required: false - name: exec_time type: number required: false - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: results type: array required: false properties: - name: error type: object required: false properties: - name: status_code type: oneOf description: >- HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: full_transcript type: string required: false - name: languages type: array required: false properties: - name: item type: string required: false - name: sentences type: array required: false properties: - name: success type: boolean required: false - name: is_empty type: boolean required: false - name: exec_time type: number required: false - name: error type: object required: false properties: - name: status_code type: oneOf description: >- HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: results type: array required: false properties: - name: item type: string required: false - name: subtitles type: array required: false properties: - name: format type: string enumValues: - srt - vtt - ass required: false - name: subtitles type: string required: false - name: utterances type: array required: false properties: - name: start type: number description: >- Start time of the utterance in seconds from session start. required: false - name: end type: number description: >- End time of the utterance in seconds from session start. required: false - name: confidence type: number description: >- Confidence score for the utterance between 0 and 1. required: false - name: channel type: integer description: >- Audio channel index (0-based) if multiple channels are present. required: false - name: words type: array description: Word-level details for this utterance. required: false properties: - name: word type: string description: Recognized token as spoken in the audio. required: false - name: start type: number description: >- Start time of the word in seconds from session start. required: false - name: end type: number description: >- End time of the word in seconds from session start. required: false - name: confidence type: number description: >- Confidence score for the token between 0 and 1. required: false - name: text type: string description: The transcribed text for the utterance. required: false - name: language type: string description: >- BCP-47 language tag detected for the utterance (e.g. "en"). required: false - name: summarization type: object required: false properties: - name: success type: boolean required: false - name: is_empty type: boolean required: false - name: exec_time type: number required: false - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: results type: string required: false - name: named_entity_recognition type: object required: false properties: - name: success type: boolean required: false - name: is_empty type: boolean required: false - name: exec_time type: number required: false - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: entity type: string required: false - name: sentiment_analysis type: object required: false properties: - name: success type: boolean required: false - name: is_empty type: boolean required: false - name: exec_time type: number required: false - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: results type: string required: false - name: chapterization type: object required: false properties: - name: success type: boolean required: false - name: is_empty type: boolean required: false - name: exec_time type: number required: false - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: results type: object required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 type: type: string const: post_final_transcript x-parser-schema-id: data: type: object properties: metadata: type: object properties: audio_duration: type: number x-parser-schema-id: number_of_distinct_channels: type: integer x-parser-schema-id: billing_time: type: number x-parser-schema-id: transcription_time: type: number x-parser-schema-id: x-parser-schema-id: transcription: *ref_11 translation: type: object properties: success: type: boolean x-parser-schema-id: is_empty: type: boolean x-parser-schema-id: exec_time: type: number x-parser-schema-id: error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: results: type: array items: type: object properties: error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: full_transcript: type: string x-parser-schema-id: languages: type: array items: type: string x-parser-schema-id: x-parser-schema-id: sentences: type: array items: *ref_12 x-parser-schema-id: subtitles: type: array items: *ref_13 x-parser-schema-id: utterances: type: array items: *ref_8 x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: summarization: type: object properties: success: type: boolean x-parser-schema-id: is_empty: type: boolean x-parser-schema-id: exec_time: type: number x-parser-schema-id: error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: results: type: string x-parser-schema-id: x-parser-schema-id: named_entity_recognition: type: object properties: success: type: boolean x-parser-schema-id: is_empty: type: boolean x-parser-schema-id: exec_time: type: number x-parser-schema-id: error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: entity: type: string x-parser-schema-id: x-parser-schema-id: sentiment_analysis: type: object properties: success: type: boolean x-parser-schema-id: is_empty: type: boolean x-parser-schema-id: exec_time: type: number x-parser-schema-id: error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: results: type: string x-parser-schema-id: x-parser-schema-id: chapterization: type: object properties: success: type: boolean x-parser-schema-id: is_empty: type: boolean x-parser-schema-id: exec_time: type: number x-parser-schema-id: error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: results: type: object x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: description: >- Final aggregated output for the session, including metadata and add-on results. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:45:00Z' type: post_final_transcript data: metadata: audio_duration: 123.45 number_of_distinct_channels: 1 billing_time: 120 transcription_time: 3.2 transcription: full_transcript: hello world x-parser-schema-id: PostFinalTranscriptMessage title: Final transcript (aggregated) description: >- This message contains the informations about the post final transcript of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:45:00Z", "type": "post_final_transcript", "data": { "metadata": { "audio_duration": 123.45, "number_of_distinct_channels": 1, "billing_time": 120, "transcription_time": 3.2 }, "transcription": { "full_transcript": "hello world" } } } bindings: [] extensions: - id: x-parser-unique-object-id value: postFinalTranscript bindings: [] extensions: *ref_0 - &ref_27 id: onPostChapterization title: On post chapterization type: send messages: - &ref_47 id: postChapterization contentType: application/json payload: - name: Chapterization description: >- This message contains the informations about the post chapterization of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: type type: string description: post_chapterization required: true - name: data type: object required: true properties: - name: results type: array required: false properties: - name: abstractive_summary type: string required: false - name: extractive_summary type: string required: false - name: summary type: string required: false - name: headline type: string required: false - name: gist type: string required: false - name: keywords type: array required: false properties: - name: item type: string required: false - name: start type: number required: false - name: end type: number required: false - name: sentences type: array required: false properties: - name: sentence type: string required: false - name: start type: number required: false - name: end type: number required: false - name: words type: array required: false properties: - name: word type: string description: Recognized token as spoken in the audio. required: false - name: start type: number description: >- Start time of the word in seconds from session start. required: false - name: end type: number description: >- End time of the word in seconds from session start. required: false - name: confidence type: number description: >- Confidence score for the token between 0 and 1. required: false - name: text type: string required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: type: type: string const: post_chapterization x-parser-schema-id: data: type: object properties: results: type: array items: type: object properties: abstractive_summary: type: string x-parser-schema-id: extractive_summary: type: string x-parser-schema-id: summary: type: string x-parser-schema-id: headline: type: string x-parser-schema-id: gist: type: string x-parser-schema-id: keywords: type: array items: type: string x-parser-schema-id: x-parser-schema-id: start: type: number x-parser-schema-id: end: type: number x-parser-schema-id: sentences: type: array items: type: object properties: sentence: type: string x-parser-schema-id: start: type: number x-parser-schema-id: end: type: number x-parser-schema-id: words: type: array items: *ref_14 x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: text: type: string x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: x-parser-schema-id: description: Post-processing output with chapter-level summaries and metadata. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:46:00Z' type: post_chapterization error: null data: results: - headline: Project kickoff start: 0 end: 60 keywords: - timeline - owner x-parser-schema-id: PostChapterizationMessage title: Chapterization description: >- This message contains the informations about the post chapterization of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:46:00Z", "type": "post_chapterization", "error": null, "data": { "results": [ { "headline": "Project kickoff", "start": 0, "end": 60, "keywords": [ "timeline", "owner" ] } ] } } bindings: [] extensions: - id: x-parser-unique-object-id value: postChapterization bindings: [] extensions: *ref_0 - &ref_28 id: onPostSummarization title: On post summarization type: send messages: - &ref_48 id: postSummarization contentType: application/json payload: - name: Summarization description: >- This message contains the informations about the post summarization of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: type type: string description: post_summarization required: true - name: data type: object required: true properties: - name: results type: string required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: type: type: string const: post_summarization x-parser-schema-id: data: type: object properties: results: type: string x-parser-schema-id: x-parser-schema-id: description: Post-processing abstractive summary of the conversation. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:47:00Z' type: post_summarization error: null data: results: The team aligned on goals and next steps for the quarter. x-parser-schema-id: PostSummarizationMessage title: Summarization description: >- This message contains the informations about the post summarization of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:47:00Z", "type": "post_summarization", "error": null, "data": { "results": "The team aligned on goals and next steps for the quarter." } } bindings: [] extensions: - id: x-parser-unique-object-id value: postSummarization bindings: [] extensions: *ref_0 - &ref_29 id: onAudioChunkAck title: On audio chunk ack type: send messages: - &ref_49 id: audioChunkAck contentType: application/json payload: - name: Audio Chunk Acknowledgment description: >- This message contains the informations about the audio chunk acknowledgment of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: acknowledged type: boolean description: >- True if the server successfully received and buffered the audio chunk. required: true - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: type type: string description: Event type for audio chunk acknowledgments. required: true - name: data type: object required: true properties: - name: byte_range type: array description: >- Inclusive byte offsets [start, end] acknowledged for this chunk. required: false properties: - name: item type: number required: false - name: time_range type: array description: >- Inclusive audio time range in seconds [start, end] covered by this chunk. required: false properties: - name: item type: number required: false headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - acknowledged - data properties: session_id: *ref_4 created_at: *ref_5 acknowledged: type: boolean description: >- True if the server successfully received and buffered the audio chunk. x-parser-schema-id: error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: type: type: string const: audio_chunk description: Event type for audio chunk acknowledgments. x-parser-schema-id: data: type: object properties: byte_range: type: array items: type: number x-parser-schema-id: minItems: 2 maxItems: 2 description: >- Inclusive byte offsets [start, end] acknowledged for this chunk. x-parser-schema-id: time_range: type: array items: type: number x-parser-schema-id: minItems: 2 maxItems: 2 description: >- Inclusive audio time range in seconds [start, end] covered by this chunk. x-parser-schema-id: x-parser-schema-id: description: >- Acknowledges receipt of an audio chunk and indicates the acknowledged byte/time ranges. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:34:56Z' type: audio_chunk acknowledged: true error: null data: byte_range: - 0 - 4095 time_range: - 0 - 0.256 x-parser-schema-id: AudioChunkAckMessage title: Audio Chunk Acknowledgment description: >- This message contains the informations about the audio chunk acknowledgment of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:34:56Z", "type": "audio_chunk", "acknowledged": true, "error": null, "data": { "byte_range": [ 0, 4095 ], "time_range": [ 0, 0.256 ] } } bindings: [] extensions: - id: x-parser-unique-object-id value: audioChunkAck bindings: [] extensions: *ref_0 - &ref_30 id: onStopRecordingAck title: On stop recording ack type: send messages: - &ref_50 id: stopRecordingAck contentType: application/json payload: - name: Stop Recording Acknowledgment description: >- This message contains the informations about the stop recording acknowledgment of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: acknowledged type: boolean description: True if stop_recording was accepted; false if rejected. required: true - name: error type: object required: false properties: - name: status_code type: oneOf description: HTTP-like code or provider-specific status string. required: false - name: exception type: string description: Short machine-readable error name. required: false - name: message type: string description: Human-readable error explanation. required: false - name: type type: string description: Event type for stop recording acknowledgments. required: true - name: data type: object description: >- Additional context provided by the provider; may be empty when acknowledged is true. required: true headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - acknowledged - data properties: session_id: *ref_4 created_at: *ref_5 acknowledged: type: boolean description: True if stop_recording was accepted; false if rejected. x-parser-schema-id: error: oneOf: - type: 'null' x-parser-schema-id: - *ref_9 x-parser-schema-id: type: type: string const: stop_recording description: Event type for stop recording acknowledgments. x-parser-schema-id: data: type: object description: >- Additional context provided by the provider; may be empty when acknowledged is true. x-parser-schema-id: description: >- Acknowledges the stop recording command with optional provider details. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:35:10Z' type: stop_recording acknowledged: true error: null data: {} - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:35:12Z' type: stop_recording acknowledged: false error: status_code: 409 exception: ConflictError message: Recording already stopped data: {} x-parser-schema-id: StopRecordingAckMessage title: Stop Recording Acknowledgment description: >- This message contains the informations about the stop recording acknowledgment of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:35:10Z", "type": "stop_recording", "acknowledged": true, "error": null, "data": {} } bindings: [] extensions: - id: x-parser-unique-object-id value: stopRecordingAck bindings: [] extensions: *ref_0 - &ref_31 id: onStartSession title: On start session type: send messages: - &ref_51 id: startSession contentType: application/json payload: - name: Start Session description: >- This message contains the informations about the start session of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: type type: string description: >- Lifecycle event emitted once when the session is created and ready. required: true headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type properties: session_id: *ref_4 created_at: *ref_5 type: type: string const: start_session description: >- Lifecycle event emitted once when the session is created and ready. x-parser-schema-id: description: Base lifecycle event for session start. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:34:00Z' type: start_session x-parser-schema-id: SimpleLifecycleMessage title: Start Session description: >- This message contains the informations about the start session of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:34:00Z", "type": "start_session" } bindings: [] extensions: - id: x-parser-unique-object-id value: startSession bindings: [] extensions: *ref_0 - &ref_32 id: onStartRecording title: On start recording type: send messages: - &ref_52 id: startRecording contentType: application/json payload: - name: Start Recording description: >- This message contains the informations about the start recording of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: type type: string description: Lifecycle event emitted when audio capture/streaming begins. required: true headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type properties: session_id: *ref_4 created_at: *ref_5 type: type: string const: start_recording description: Lifecycle event emitted when audio capture/streaming begins. x-parser-schema-id: description: Lifecycle event indicating the start of recording. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:34:05Z' type: start_recording x-parser-schema-id: SimpleLifecycleMessageStart title: Start Recording description: >- This message contains the informations about the start recording of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:34:05Z", "type": "start_recording" } bindings: [] extensions: - id: x-parser-unique-object-id value: startRecording bindings: [] extensions: *ref_0 - &ref_33 id: onEndRecording title: On end recording type: send messages: - &ref_53 id: endRecording contentType: application/json payload: - name: End Recording description: >- This message contains the informations about the end recording of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: type type: string description: >- Lifecycle event emitted when the provider has stopped receiving audio. required: true - name: data type: object description: >- Provider-defined object with optional metadata related to the end of recording. required: true headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type - data properties: session_id: *ref_4 created_at: *ref_5 type: type: string const: end_recording description: >- Lifecycle event emitted when the provider has stopped receiving audio. x-parser-schema-id: data: type: object additionalProperties: true description: >- Provider-defined object with optional metadata related to the end of recording. x-parser-schema-id: description: >- Lifecycle event sent when recording has ended, optionally carrying provider metadata. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:36:00Z' type: end_recording data: reason: user_request received_total_bytes: 1048576 x-parser-schema-id: EndRecordingMessage title: End Recording description: >- This message contains the informations about the end recording of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:36:00Z", "type": "end_recording", "data": { "reason": "user_request", "received_total_bytes": 1048576 } } bindings: [] extensions: - id: x-parser-unique-object-id value: endRecording bindings: [] extensions: *ref_0 - &ref_34 id: onEndSession title: On end session type: send messages: - &ref_54 id: endSession contentType: application/json payload: - name: End Session description: >- This message contains the informations about the end session of the audio chunk. type: object properties: - name: session_id type: string description: UUID identifying the session. examples: *ref_1 required: true - name: created_at type: string description: ISO 8601 timestamp in UTC. examples: *ref_2 required: true - name: type type: string description: >- Lifecycle event emitted when the session is closed and no further data will be sent. required: true headers: [] jsonPayloadSchema: type: object required: - session_id - created_at - type properties: session_id: *ref_4 created_at: *ref_5 type: type: string const: end_session description: >- Lifecycle event emitted when the session is closed and no further data will be sent. x-parser-schema-id: description: Lifecycle event for session termination. examples: - session_id: 550e8400-e29b-41d4-a716-446655440000 created_at: '2025-09-19T12:36:05Z' type: end_session x-parser-schema-id: SimpleLifecycleMessageEndSession title: End Session description: >- This message contains the informations about the end session of the audio chunk. example: |- { "session_id": "550e8400-e29b-41d4-a716-446655440000", "created_at": "2025-09-19T12:36:05Z", "type": "end_session" } bindings: [] extensions: - id: x-parser-unique-object-id value: endSession bindings: [] extensions: *ref_0 sendOperations: - *ref_15 - *ref_16 - *ref_17 receiveOperations: - *ref_18 - *ref_19 - *ref_20 - *ref_21 - *ref_22 - *ref_23 - *ref_24 - *ref_25 - *ref_26 - *ref_27 - *ref_28 - *ref_29 - *ref_30 - *ref_31 - *ref_32 - *ref_33 - *ref_34 sendMessages: - *ref_35 - *ref_36 - *ref_37 receiveMessages: - *ref_38 - *ref_39 - *ref_40 - *ref_41 - *ref_42 - *ref_43 - *ref_44 - *ref_45 - *ref_46 - *ref_47 - *ref_48 - *ref_49 - *ref_50 - *ref_51 - *ref_52 - *ref_53 - *ref_54 extensions: - id: x-parser-unique-object-id value: liveTranscription securitySchemes: [] ````