> This page is for Expression Measurement. > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://dev.hume.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://dev.hume.ai/_mcp/server. # Stream audio GET /v1/expression/audio/realtime Stream audio from a microphone or a file and receive expression measurements as speech happens. You do not need to detect speech or split it into segments: the server detects each stretch of speech and measures it while it is still being spoken. ## Sending audio Send audio as binary messages of signed 16-bit little-endian PCM, mono, 16 kHz, with no header. Frames of around 100 ms work well. You can cut the audio at any sample boundary; the server joins the frames into one continuous stream. - **Configuration:** send `session.update` before your first audio frame. A `session.update` after your first audio frame ends the session with `config_invalid`. - **Rejected frames:** a frame that is empty, has an odd number of bytes, or holds more than 10 seconds of audio gets `invalid_audio_frame`, and the session continues. A message over 1MiB ends the session with `message_too_large`. Accepted frames are not acknowledged. - **Send rate:** stream audio in close to real time, no faster than 1 second of audio per second. A frame sent faster can get `rate_limited`, and none of its audio is measured. Wait briefly and resend the same frame, so that the stream stays continuous. To measure a recording faster than it plays, use the audio file endpoint. - **Failures:** if measurement fails, you receive `internal_error` and the session ends. Open a new connection. ## How measurements are produced The server detects when speech starts and stops. Each continuous stretch of speech is an **utterance**, bracketed by `utterance.start` and `utterance.end`. - **During speech:** a `measurement.result` arrives every `measurement_timer_ms` milliseconds of speech, with `trigger` set to `interval`. - **When speech ends:** a final measurement arrives with `trigger` set to `speech_ended`, unless the previous measurement ended less than one second earlier. Every utterance gets at least one measurement. - **Span:** each measurement covers the most recent 10 seconds of the utterance, or the whole utterance if it is shorter, so consecutive measurements can overlap. `audio_start_ms` and `audio_end_ms` give the span, counted from the start of the audio the server has accepted. - **Ending the session:** `session.close` during speech ends the utterance. You receive its final measurement, if one is due, then `utterance.end`, then `session.closed`. A session that ends with an error can leave its last utterance without an `utterance.end`. ## Limits | Limit | Value | |---|---| | Audio per frame | 10 seconds (320KB) | | Message size | 1MiB (1,048,576 bytes) | | Send rate | 1 second of audio per second | ## Message flow A session at the default `measurement_timer_ms` of 3000, with one utterance: speech begins 98 ms into the audio and is still in progress at 26000 ms, when `session.close` ends it. | Time in audio | Direction | Message | |---|---|---| | on connect | receive | `session.created` | | before audio | send | `session.update` (if you change the configuration) | | before audio | receive | `session.updated` (if you sent `session.update`) | | 0 ms onward | send | audio frames | | 98 ms | receive | `utterance.start` (utterance 0) | | 3098 ms | receive | `measurement.result` (98 to 3098 ms, `interval`) | | 6098 ms | receive | `measurement.result` (98 to 6098 ms, `interval`) | | 9098 to 24098 ms | receive | `measurement.result` every 3000 ms of speech (six more, each covering at most the most recent 10 seconds) | | 26000 ms | send | `session.close` | | 26000 ms | receive | `measurement.result` (16000 to 26000 ms, `speech_ended`) | | 26000 ms | receive | `utterance.end` (utterance 0) | | 26000 ms | receive | `session.closed` (`produced.utterances` 1, `produced.measurements` 9) | Reference: https://dev.hume.ai/expression-measurement/reference/audio/stream-audio ## AsyncAPI Specification ```yaml asyncapi: 2.6.0 info: title: Stream audio version: subpackage_audio.Stream audio description: >- Stream audio from a microphone or a file and receive expression measurements as speech happens. You do not need to detect speech or split it into segments: the server detects each stretch of speech and measures it while it is still being spoken. ## Sending audio Send audio as binary messages of signed 16-bit little-endian PCM, mono, 16 kHz, with no header. Frames of around 100 ms work well. You can cut the audio at any sample boundary; the server joins the frames into one continuous stream. - **Configuration:** send `session.update` before your first audio frame. A `session.update` after your first audio frame ends the session with `config_invalid`. - **Rejected frames:** a frame that is empty, has an odd number of bytes, or holds more than 10 seconds of audio gets `invalid_audio_frame`, and the session continues. A message over 1MiB ends the session with `message_too_large`. Accepted frames are not acknowledged. - **Send rate:** stream audio in close to real time, no faster than 1 second of audio per second. A frame sent faster can get `rate_limited`, and none of its audio is measured. Wait briefly and resend the same frame, so that the stream stays continuous. To measure a recording faster than it plays, use the audio file endpoint. - **Failures:** if measurement fails, you receive `internal_error` and the session ends. Open a new connection. ## How measurements are produced The server detects when speech starts and stops. Each continuous stretch of speech is an **utterance**, bracketed by `utterance.start` and `utterance.end`. - **During speech:** a `measurement.result` arrives every `measurement_timer_ms` milliseconds of speech, with `trigger` set to `interval`. - **When speech ends:** a final measurement arrives with `trigger` set to `speech_ended`, unless the previous measurement ended less than one second earlier. Every utterance gets at least one measurement. - **Span:** each measurement covers the most recent 10 seconds of the utterance, or the whole utterance if it is shorter, so consecutive measurements can overlap. `audio_start_ms` and `audio_end_ms` give the span, counted from the start of the audio the server has accepted. - **Ending the session:** `session.close` during speech ends the utterance. You receive its final measurement, if one is due, then `utterance.end`, then `session.closed`. A session that ends with an error can leave its last utterance without an `utterance.end`. ## Limits | Limit | Value | |---|---| | Audio per frame | 10 seconds (320KB) | | Message size | 1MiB (1,048,576 bytes) | | Send rate | 1 second of audio per second | ## Message flow A session at the default `measurement_timer_ms` of 3000, with one utterance: speech begins 98 ms into the audio and is still in progress at 26000 ms, when `session.close` ends it. | Time in audio | Direction | Message | |---|---|---| | on connect | receive | `session.created` | | before audio | send | `session.update` (if you change the configuration) | | before audio | receive | `session.updated` (if you sent `session.update`) | | 0 ms onward | send | audio frames | | 98 ms | receive | `utterance.start` (utterance 0) | | 3098 ms | receive | `measurement.result` (98 to 3098 ms, `interval`) | | 6098 ms | receive | `measurement.result` (98 to 6098 ms, `interval`) | | 9098 to 24098 ms | receive | `measurement.result` every 3000 ms of speech (six more, each covering at most the most recent 10 seconds) | | 26000 ms | send | `session.close` | | 26000 ms | receive | `measurement.result` (16000 to 26000 ms, `speech_ended`) | | 26000 ms | receive | `utterance.end` (utterance 0) | | 26000 ms | receive | `session.closed` (`produced.utterances` 1, `produced.measurements` 9) | channels: /v1/expression/audio/realtime: description: >- Stream audio from a microphone or a file and receive expression measurements as speech happens. You do not need to detect speech or split it into segments: the server detects each stretch of speech and measures it while it is still being spoken. ## Sending audio Send audio as binary messages of signed 16-bit little-endian PCM, mono, 16 kHz, with no header. Frames of around 100 ms work well. You can cut the audio at any sample boundary; the server joins the frames into one continuous stream. - **Configuration:** send `session.update` before your first audio frame. A `session.update` after your first audio frame ends the session with `config_invalid`. - **Rejected frames:** a frame that is empty, has an odd number of bytes, or holds more than 10 seconds of audio gets `invalid_audio_frame`, and the session continues. A message over 1MiB ends the session with `message_too_large`. Accepted frames are not acknowledged. - **Send rate:** stream audio in close to real time, no faster than 1 second of audio per second. A frame sent faster can get `rate_limited`, and none of its audio is measured. Wait briefly and resend the same frame, so that the stream stays continuous. To measure a recording faster than it plays, use the audio file endpoint. - **Failures:** if measurement fails, you receive `internal_error` and the session ends. Open a new connection. ## How measurements are produced The server detects when speech starts and stops. Each continuous stretch of speech is an **utterance**, bracketed by `utterance.start` and `utterance.end`. - **During speech:** a `measurement.result` arrives every `measurement_timer_ms` milliseconds of speech, with `trigger` set to `interval`. - **When speech ends:** a final measurement arrives with `trigger` set to `speech_ended`, unless the previous measurement ended less than one second earlier. Every utterance gets at least one measurement. - **Span:** each measurement covers the most recent 10 seconds of the utterance, or the whole utterance if it is shorter, so consecutive measurements can overlap. `audio_start_ms` and `audio_end_ms` give the span, counted from the start of the audio the server has accepted. - **Ending the session:** `session.close` during speech ends the utterance. You receive its final measurement, if one is due, then `utterance.end`, then `session.closed`. A session that ends with an error can leave its last utterance without an `utterance.end`. ## Limits | Limit | Value | |---|---| | Audio per frame | 10 seconds (320KB) | | Message size | 1MiB (1,048,576 bytes) | | Send rate | 1 second of audio per second | ## Message flow A session at the default `measurement_timer_ms` of 3000, with one utterance: speech begins 98 ms into the audio and is still in progress at 26000 ms, when `session.close` ends it. | Time in audio | Direction | Message | |---|---|---| | on connect | receive | `session.created` | | before audio | send | `session.update` (if you change the configuration) | | before audio | receive | `session.updated` (if you sent `session.update`) | | 0 ms onward | send | audio frames | | 98 ms | receive | `utterance.start` (utterance 0) | | 3098 ms | receive | `measurement.result` (98 to 3098 ms, `interval`) | | 6098 ms | receive | `measurement.result` (98 to 6098 ms, `interval`) | | 9098 to 24098 ms | receive | `measurement.result` every 3000 ms of speech (six more, each covering at most the most recent 10 seconds) | | 26000 ms | send | `session.close` | | 26000 ms | receive | `measurement.result` (16000 to 26000 ms, `speech_ended`) | | 26000 ms | receive | `utterance.end` (utterance 0) | | 26000 ms | receive | `session.closed` (`produced.utterances` 1, `produced.measurements` 9) | publish: operationId: subpackage_audio.Stream audio-publish summary: Server messages message: oneOf: - $ref: >- #/components/messages/subpackage_audio.Stream audio-server-0-audioReceiveSessionCreated - $ref: >- #/components/messages/subpackage_audio.Stream audio-server-1-audioReceiveSessionUpdated - $ref: >- #/components/messages/subpackage_audio.Stream audio-server-2-audioReceiveUtteranceStart - $ref: >- #/components/messages/subpackage_audio.Stream audio-server-3-audioReceiveMeasurementResult - $ref: >- #/components/messages/subpackage_audio.Stream audio-server-4-audioReceiveUtteranceEnd - $ref: >- #/components/messages/subpackage_audio.Stream audio-server-5-audioReceiveError - $ref: >- #/components/messages/subpackage_audio.Stream audio-server-6-audioReceiveSessionClosed subscribe: operationId: subpackage_audio.Stream audio-subscribe summary: Client messages message: oneOf: - $ref: >- #/components/messages/subpackage_audio.Stream audio-client-0-audioSendSessionUpdate - $ref: >- #/components/messages/subpackage_audio.Stream audio-client-1-audioSendSessionClose - $ref: >- #/components/messages/subpackage_audio.Stream audio-client-2-audioSendAudioFrame servers: Production: url: wss://api.cloud.hume.ai/ protocol: wss x-default: true components: messages: subpackage_audio.Stream audio-server-0-audioReceiveSessionCreated: name: audioReceiveSessionCreated title: session.created description: >- Sent when the connection opens, before you send anything. Carries the session ID and the default configuration, which stays in effect unless you change it with `session.update`. payload: $ref: '#/components/schemas/audio_sessionCreated' subpackage_audio.Stream audio-server-1-audioReceiveSessionUpdated: name: audioReceiveSessionUpdated title: session.updated description: >- Sent when a `session.update` is accepted. Carries the full configuration now in effect, including defaults for any fields you omitted. payload: $ref: '#/components/schemas/audio_sessionUpdated' subpackage_audio.Stream audio-server-2-audioReceiveUtteranceStart: name: audioReceiveUtteranceStart title: utterance.start description: >- Sent when speech starts. Every `measurement.result` until the matching `utterance.end` belongs to this utterance. payload: $ref: '#/components/schemas/audio_utteranceStart' subpackage_audio.Stream audio-server-3-audioReceiveMeasurementResult: name: audioReceiveMeasurementResult title: measurement.result description: >- Sent every `measurement_timer_ms` of speech while an utterance is in progress, and once more when the utterance ends unless the previous measurement ended less than one second earlier. Each measurement covers up to the most recent 10 seconds of the utterance. payload: $ref: '#/components/schemas/audio_measurementResult' subpackage_audio.Stream audio-server-4-audioReceiveUtteranceEnd: name: audioReceiveUtteranceEnd title: utterance.end description: >- Sent when speech stops, after the utterance's final `measurement.result`, so every measurement for the utterance has arrived by the time you receive it. payload: $ref: '#/components/schemas/audio_utteranceEnd' subpackage_audio.Stream audio-server-5-audioReceiveError: name: audioReceiveError title: error description: >- Sent when a message you sent is rejected or the server fails to process it. For a recoverable error the message is rejected and the session continues; for a session-ending error, `session.closed` with `reason` `error` follows. `ErrorCode` lists each code, its class, and what to do. payload: $ref: '#/components/schemas/audio_error' subpackage_audio.Stream audio-server-6-audioReceiveSessionClosed: name: audioReceiveSessionClosed title: session.closed description: >- Sent as the last message of the session, after any final measurement and `utterance.end`. Carries the reason the session ended and totals of what was received and produced. The connection closes immediately after it, with the close code for the `reason`. payload: $ref: '#/components/schemas/audio_sessionClosed' subpackage_audio.Stream audio-client-0-audioSendSessionUpdate: name: audioSendSessionUpdate title: session.update description: >- Replaces the whole configuration; any field you omit returns to its default. Send it before your first audio frame, because once audio has been accepted a `session.update` ends the session with `config_invalid`. The server confirms with `session.updated`, or ends the session with `config_invalid` if the message contains an unrecognized field or an unsupported value. payload: $ref: '#/components/schemas/audio_sessionUpdate' subpackage_audio.Stream audio-client-1-audioSendSessionClose: name: audioSendSessionClose title: session.close description: >- Ends the session. The server sends any final results, then `session.closed`, and closes the connection with code 1000; on the audio endpoint, if the final measurement fails, `error` and `session.closed` with `reason` `error` follow instead. Prefer this to closing the WebSocket yourself, which ends the session immediately and discards any final results and the totals. payload: $ref: '#/components/schemas/audio_sessionClose' subpackage_audio.Stream audio-client-2-audioSendAudioFrame: name: audioSendAudioFrame title: audio frame description: >- A binary message of signed 16-bit little-endian PCM audio, mono, 16 kHz, with no header. The server appends it to the session's audio and measures speech as it is detected; accepted frames are not acknowledged. A frame that is empty, does not contain whole samples, or exceeds the frame limit is rejected with `invalid_audio_frame`, and a frame that arrives faster than the send rate can be rejected with `rate_limited`; in both cases the session continues. payload: $ref: '#/components/schemas/audio_audioFrame' schemas: SessionId: type: string format: uuid description: >- Unique identifier for the session. It is also the `run_id` of the run the session is recorded as. Include it when contacting support about a session. title: SessionId AudioConfig: type: object properties: type: type: string enum: - audio/pcm encoding: type: string enum: - s16le description: The sample encoding. `s16le` is signed 16-bit little-endian PCM. sample_rate: type: integer description: The sample rate in Hz. channels: type: integer required: - type - encoding - sample_rate - channels description: The audio format. title: AudioConfig MeasurementTimerMs: type: integer minimum: 3000 maximum: 10000 description: >- The interval between measurements while speech is in progress, in milliseconds of speech. title: MeasurementTimerMs audio_sessionCreated: type: object properties: type: type: string enum: - session.created session_id: $ref: '#/components/schemas/SessionId' audio: $ref: '#/components/schemas/AudioConfig' measurement_timer_ms: $ref: '#/components/schemas/MeasurementTimerMs' required: - type - session_id - audio - measurement_timer_ms description: >- The session ID and the configuration in effect when the connection opened. title: audio_sessionCreated audio_sessionUpdated: type: object properties: type: type: string enum: - session.updated audio: $ref: '#/components/schemas/AudioConfig' measurement_timer_ms: $ref: '#/components/schemas/MeasurementTimerMs' required: - type - audio - measurement_timer_ms description: >- The full configuration in effect after a `session.update`, including defaults for any fields you omitted. title: audio_sessionUpdated audio_utteranceStart: type: object properties: type: type: string enum: - utterance.start utterance_id: type: integer minimum: 0 description: >- Sequential identifier of the utterance within the session, starting at 0. audio_start_ms: type: integer minimum: 0 description: >- Where speech started, in milliseconds from the start of the session's audio. required: - type - utterance_id - audio_start_ms description: >- The start of an utterance. Every `measurement.result` until the matching `utterance.end` belongs to it. title: audio_utteranceStart MeasurementTrigger: type: string enum: - interval - speech_ended description: >- Why the measurement was produced. - `interval`: the measurement interval (`measurement_timer_ms`) elapsed while speech continued. - `speech_ended`: the utterance ended, or the audio ended while speech was in progress. A final measurement is skipped when the previous one ended less than one second earlier, so the last measurement of an utterance may carry the trigger `interval`. Where an utterance ended is reported separately: as an `utterance.end` message in a realtime session, and in `utterances` in an audio file response. title: MeasurementTrigger AudioExpressionName: type: string description: >- The name of an expression that can be detected in speech; see the [full list of audio expressions](/expression-measurement/docs/audio/measurements#expressions). Names are lowercase and may contain spaces and punctuation. New names may be added over time; treat a name you do not recognize as a new prediction. title: AudioExpressionName AudioExpressionScore: type: object properties: name: $ref: '#/components/schemas/AudioExpressionName' probability: type: number format: double minimum: 0 maximum: 1 description: >- The probability that this expression is present, rounded to four decimal places. required: - name - probability description: A scored expression detected in the speech. title: AudioExpressionScore VoiceAttributeName: type: string description: >- The name of a quality of the voice or the audio, such as a manner of speaking, a vocal timbre or a background sound; see the [full list of voice attributes](/expression-measurement/docs/audio/measurements#voice-attributes). Names are lowercase and may contain spaces and punctuation. New names may be added over time; treat a name you do not recognize as a new prediction. title: VoiceAttributeName VoiceAttributeScore: type: object properties: name: $ref: '#/components/schemas/VoiceAttributeName' probability: type: number format: double minimum: 0 maximum: 1 description: >- The probability that this quality is present, rounded to four decimal places. required: - name - probability description: A scored quality of the voice or the audio. title: VoiceAttributeScore audio_measurementResult: type: object properties: type: type: string enum: - measurement.result measurement_id: type: integer minimum: 0 description: >- Sequential identifier of the measurement within the session, starting at 0. utterance_id: type: integer minimum: 0 description: >- The utterance this measurement belongs to, as given in `utterance.start`. audio_start_ms: type: integer minimum: 0 description: >- Start of the window measured, in milliseconds from the start of the session's audio. Never earlier than the start of the utterance. audio_end_ms: type: integer minimum: 0 description: >- End of the window measured, in milliseconds from the start of the session's audio. trigger: $ref: '#/components/schemas/MeasurementTrigger' expressions: type: array items: $ref: '#/components/schemas/AudioExpressionScore' description: >- Expressions detected in the speech, such as `joy`, `anger` and `chuckling`, in descending order of probability. Scores with equal probability are ordered by the model's underlying score, then by name. Only expressions judged present are included, each against a threshold set for that expression, so the array may be empty. `probability` is the measured chance that the expression is truly present. voice_attributes: type: array items: $ref: '#/components/schemas/VoiceAttributeScore' description: >- Qualities of the voice and the audio, such as `husky`, `fast` and `background music`, in descending order of probability. Scores with equal probability are ordered by the model's underlying score, then by name. Only scores of 0.725 or above are included, so the array may be empty. `probability` is calibrated: the expected intensity a human rater would give the quality. required: - type - measurement_id - utterance_id - audio_start_ms - audio_end_ms - trigger - expressions - voice_attributes description: >- Expression measurements for a window of an utterance. The window spans `audio_start_ms` to `audio_end_ms` and covers up to the most recent 10 seconds of the utterance. An interval measurement taken as speech stops can end shortly after the utterance does. Consecutive measurements of an utterance overlap, except interval measurements at a `measurement_timer_ms` of 10000, which meet end to end. title: audio_measurementResult audio_utteranceEnd: type: object properties: type: type: string enum: - utterance.end utterance_id: type: integer minimum: 0 description: The utterance that ended, as given in `utterance.start`. audio_start_ms: type: integer minimum: 0 description: >- Where the utterance started, in milliseconds from the start of the session's audio. Matches the `utterance.start` message. audio_end_ms: type: integer minimum: 0 description: >- Where the utterance ended, in milliseconds from the start of the session's audio. required: - type - utterance_id - audio_start_ms - audio_end_ms description: The end of an utterance, with its full extent in the audio. title: audio_utteranceEnd ErrorCode: type: string enum: - invalid_audio_frame - invalid_image_frame - message_invalid - rate_limited - config_invalid - message_too_large - internal_error description: >- Identifies what went wrong and whether the session continues. **Recoverable.** The message is rejected and the session continues. - `invalid_audio_frame`: the audio frame was empty, had an odd number of bytes, or held more than 10 seconds of audio. Check how you slice audio and keep sending. Audio only. - `invalid_image_frame`: the frame was empty, was not a JPEG, or exceeded the pixel limit. Check the image and keep sending. Video only. - `message_invalid`: a text message was not valid JSON, had no `type`, or had an unrecognized `type`. Correct the message and keep sending. - `rate_limited`: media arrived faster than the send rate and was not processed. Audio: wait briefly and send the same frame again, so that the stream stays continuous. Video: from a live camera, drop the frame and send the next; from a recording, wait briefly and send the same frame again. **Depends on the endpoint.** - `internal_error`: the server failed while processing media. Audio: the session ends as for a session-ending error; open a new connection. Video: the frame is skipped and the session continues; resend it if you need a result for it. Five consecutive failures end the session; frames that are rejected or have no faces to measure do not reset the count. **Session-ending.** `error` is followed by `session.closed` with `reason` `error`, and the connection closes with code 1008. - `config_invalid`: a `session.update` contained an unrecognized field or an unsupported value, or arrived after you started sending media. Correct the message and open a new connection. - `message_too_large`: a message exceeded the size limit. Reduce the frame size and open a new connection. title: ErrorCode audio_error: type: object properties: type: type: string enum: - error code: $ref: '#/components/schemas/ErrorCode' message: type: string description: >- A human-readable description of the error, intended for logging and debugging. The wording may change; use `code` for programmatic handling. retryable: type: boolean description: >- `false` for every error that ends the session. `true` for every error the session survives, except `internal_error` on the video endpoint, where it reports whether the failure was temporary and the frame is worth resending. required: - type - code - message - retryable description: >- A rejected message or a processing failure. `code` says what happened and whether the session continues. title: audio_error CloseReason: type: string enum: - client_request - server_shutdown - idle_timeout - error description: >- Why the session ended. `session.closed` is the last message, and the WebSocket close code that follows it depends on the reason. - `client_request`: you sent `session.close`. Close code 1000. - `server_shutdown`: the server is restarting; reconnect at once to start a new session. Close code 1012. - `idle_timeout`: the server received no media frame it could use for 30 seconds; open a new session to continue. Close code 1000. - `error`: a session-ending error, reported in the preceding `error` message. Close code 1008. title: CloseReason AudioReceived: type: object properties: audio_duration_ms: type: integer minimum: 0 description: >- Total duration of audio accepted, in milliseconds, whether or not it contained speech. frames: type: integer minimum: 0 description: >- Number of audio frames accepted. Frames rejected with an error are not counted, so comparing this with the number you sent tells you how many were rejected. required: - audio_duration_ms - frames description: What the server received during the session. title: AudioReceived AudioProduced: type: object properties: utterances: type: integer minimum: 0 description: Number of utterances detected. measurements: type: integer minimum: 0 description: >- Number of `measurement.result` messages sent. This counts messages; the video endpoint's field of the same name counts faces. required: - utterances - measurements description: What the server produced during the session. title: AudioProduced audio_sessionClosed: type: object properties: type: type: string enum: - session.closed session_id: $ref: '#/components/schemas/SessionId' reason: $ref: '#/components/schemas/CloseReason' received: $ref: '#/components/schemas/AudioReceived' produced: $ref: '#/components/schemas/AudioProduced' required: - type - session_id - reason - received - produced description: Why the session ended, and totals of what was received and produced. title: audio_sessionClosed AudioConfigUpdate: type: object properties: type: type: string enum: - audio/pcm default: audio/pcm encoding: type: string enum: - s16le default: s16le description: The sample encoding. `s16le` is signed 16-bit little-endian PCM. sample_rate: type: integer default: 16000 description: The sample rate in Hz. channels: type: integer default: 1 description: >- The format of the audio you send. Only one format is supported; any other value is rejected with `config_invalid`. title: AudioConfigUpdate audio_sessionUpdate: type: object properties: type: type: string enum: - session.update audio: $ref: '#/components/schemas/AudioConfigUpdate' measurement_timer_ms: type: integer minimum: 3000 maximum: 10000 default: 3000 description: >- The interval between measurements while speech is in progress, in milliseconds of speech. Lower values produce measurements more often; at the maximum, interval measurements are back to back rather than overlapping. required: - type description: >- The configuration to apply to the session. Omitted fields are reset to their defaults. title: audio_sessionUpdate audio_sessionClose: type: object properties: type: type: string enum: - session.close required: - type description: A request to end the session. title: audio_sessionClose audio_audioFrame: type: string format: binary description: >- Raw audio: signed 16-bit little-endian PCM, mono, 16 kHz, with no header. A frame must be non-empty, contain whole samples, and stay within the frame limit given in the channel description. Frame boundaries do not need to align with anything. title: audio_audioFrame ```