For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
<llms-only>
> For the complete documentation index, see [llms.txt](https://www.assemblyai.com/docs/llms.txt)
</llms-only>
Stream audio and receive real-time transcription results. Fast, cost-effective streaming transcription available in three variants:
- **Universal-Streaming English** — the fastest real-time English transcription
- **Universal-Streaming Multilingual** — multilingual support (English, Spanish, German, French, Portuguese, and Italian) at the same speed and price
- **Whisper-Streaming** — open-source Whisper powered by AssemblyAI's infrastructure with 99+ languages
<Note> To use our EU server for Streaming STT, replace `streaming.assemblyai.com` with
`streaming.eu.assemblyai.com`. </Note>
Stream audio and receive real-time transcription results. Fast, cost-effective streaming transcription available in three variants:
Universal-Streaming English — the fastest real-time English transcription
Universal-Streaming Multilingual — multilingual support (English, Spanish, German, French, Portuguese, and Italian) at the same speed and price
Whisper-Streaming — open-source Whisper powered by AssemblyAI’s infrastructure with 99+ languages
To use our EU server for Streaming STT, replace streaming.assemblyai.com with
streaming.eu.assemblyai.com.
Handshake
WSS
wss://streaming.assemblyai.com/v3/ws
Headers
AuthorizationstringOptional
Use your API key for authentication, or alternatively generate a temporary token and pass it via the token query parameter.
Query parameters
speech_modelenumRequired
The speech model used for your Streaming session.
Allowed values:
encodingenumOptionalDefaults to pcm_s16le
Encoding of the audio stream.
Allowed values:
format_turnsenumOptionalDefaults to false
Whether to return formatted final transcripts with punctuation, casing, and inverse text normalization (e.g. dates, times, phone numbers). Does not control digit rendering.
Allowed values:
inactivity_timeoutintegerOptional5-3600
Optional time in seconds of inactivity before session is terminated. If not set, no inactivity timeout is applied.
keyterms_promptlist of stringsOptional
A list of words and phrases to improve recognition accuracy for. See [Keyterms Prompting](https://www.assemblyai.com/docs/streaming/keyterms-prompting) for more details.
language_detectionenumOptionalDefaults to false
Whether to detect the language and return language metadata on utterances and final turns. Only available for the multilingual model.
Allowed values:
max_turn_silenceintegerOptionalDefaults to 1280
The maximum amount of silence in milliseconds allowed in a turn before end of turn is triggered. See [Turn Detection](https://www.assemblyai.com/docs/streaming/universal-streaming/turn-detection) for configuration details.
min_turn_silenceintegerOptionalDefaults to 400
The minimum amount of silence in milliseconds required to detect end of turn when confident. See [Turn Detection](https://www.assemblyai.com/docs/streaming/universal-streaming/turn-detection) for configuration details.
sample_rateintegerRequiredDefaults to 16000
Sample rate of the audio stream.
speaker_labelsenumOptionalDefaults to false
Whether to enable [Streaming Speaker Diarization](https://www.assemblyai.com/docs/streaming/label-speakers-and-separate-channels). When enabled, each Turn event will include a `speaker_label` field and each final word in the `words` array will include a `speaker` field for word-level speaker attribution.
Allowed values:
max_speakersintegerOptional1-10
The maximum number of speakers expected in the audio stream (1-10). Setting this can improve speaker label accuracy when you know the number of speakers in advance. Only used when `speaker_labels` is enabled. See [Streaming Diarization](https://www.assemblyai.com/docs/streaming/label-speakers-and-separate-channels) for more details.
The confidence threshold (0.0 to 1.0) for classifying audio frames as silence. Frames with VAD confidence below this value are considered silent. Increase for noisy environments to reduce false speech detection.
end_of_turn_confidence_thresholddoubleOptionalDefaults to 0.4
The confidence threshold (0.0 to 1.0) to use when determining if the end of a turn has been reached. See [Turn Detection](https://www.assemblyai.com/docs/streaming/universal-streaming/turn-detection) for configuration details.
Note: This parameter is only supported for the Universal-streaming model.
domainenumOptional
Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to `"medical-v1"` to enable [Medical Mode](https://www.assemblyai.com/docs/streaming/medical-mode) for improved accuracy of medical terms such as medications, procedures, conditions, and dosages. Supported languages: English (`en`), Spanish (`es`), German (`de`), French (`fr`). If used with an unsupported language, the parameter is ignored and a warning is returned.
Allowed values:
languageenumOptionalDefaults to enDeprecated
The language of your audio stream.
Allowed values:
llm_gatewaystringRequired
JSON-stringified LLM Gateway configuration that processes each finalized turn. Follows the same interface as the [Chat Completions](/docs/llm-gateway/chat-completions) endpoint and accepts `model`, `messages`, `tools`, `tool_choice`, `post_processing_steps`, and `max_tokens`. See [Apply LLM Gateway to Streaming](https://www.assemblyai.com/docs/llm-gateway/apply-llm-gateway-to-streaming) for the full schema and examples.
Send
sendAudiostringRequiredformat: "binary"
Send audio data chunks for transcription. The payload must be of type bytes and contain audio data between 50ms and 1000ms in length. When streaming from a pre-recorded file, pace the chunks at approximately real-time (for example, sleep for the chunk’s duration between sends) — sending chunks in a tight loop can produce inconsistent Turn messages.
OR
sendUpdateConfigurationobjectRequired
Update streaming configuration parameters during an active session.
OR
sendForceEndpointobjectRequired
Manually force an endpoint in the transcription.
OR
sendSessionTerminationobjectRequired
Gracefully terminate the streaming session.
OR
sendKeepAliveobjectRequired
Send a keep-alive message to reset the `inactivity_timeout` timer. This is not necessary by default — sessions remain open until explicitly terminated or until the 3-hour maximum session duration is reached. This message is only needed if you have set `inactivity_timeout` and want to keep the session open during periods where no audio is being sent.
Receive
receiveSessionBeginsobjectRequired
Receive confirmation that the streaming session has successfully started.
OR
receiveTurnobjectRequired
Receive a formatted turn-based transcription result.
OR
receiveTerminationobjectRequired
Receive confirmation that the session has been terminated by the server.
OR
receiveLLMGatewayResponseobjectRequired
Receive an LLM Gateway response for a finalized turn. Emitted once per turn when llm_gateway is configured on the connection.
A list of words and phrases to improve recognition accuracy for. See Keyterms Prompting for more details.
The maximum amount of silence in milliseconds allowed in a turn before end of turn is triggered. See Turn Detection for configuration details.
The minimum amount of silence in milliseconds required to detect end of turn when confident. See Turn Detection for configuration details.
Whether to enable Streaming Speaker Diarization. When enabled, each Turn event will include a speaker_label field and each final word in the words array will include a speaker field for word-level speaker attribution.
The maximum number of speakers expected in the audio stream (1-10). Setting this can improve speaker label accuracy when you know the number of speakers in advance. Only used when speaker_labels is enabled. See Streaming Diarization for more details.
The confidence threshold (0.0 to 1.0) to use when determining if the end of a turn has been reached. See Turn Detection for configuration details.
Note: This parameter is only supported for the Universal-streaming model.
Enable domain-specific transcription models to improve accuracy for specialized terminology. Set to "medical-v1" to enable Medical Mode for improved accuracy of medical terms such as medications, procedures, conditions, and dosages. Supported languages: English (en), Spanish (es), German (de), French (fr). If used with an unsupported language, the parameter is ignored and a warning is returned.
JSON-stringified LLM Gateway configuration that processes each finalized turn. Follows the same interface as the Chat Completions endpoint and accepts model, messages, tools, tool_choice, post_processing_steps, and max_tokens. See Apply LLM Gateway to Streaming for the full schema and examples.
Send a keep-alive message to reset the inactivity_timeout timer. This is not necessary by default — sessions remain open until explicitly terminated or until the 3-hour maximum session duration is reached. This message is only needed if you have set inactivity_timeout and want to keep the session open during periods where no audio is being sent.
