Skip to main content

Documentation Index

Fetch the complete documentation index at: https://developer.suki.ai/llms.txt

Use this file to discover all available pages before exploring further.

After you create an ambient session and seed the session context, you can stream audio to the session using the GET /ws/stream endpoint for ambient sessions or the GET /ws/transcribe endpoint for dictation sessions. Both endpoints use WebSocket to stream audio.
This guide applies to: Direct HTTP and WebSocket integrations with Suki for Partner Ambient, Form Filling, and Dictation APIs.
EndpointPurposeAPI reference
GET ws/streamStream PCM audio into an ambient and a form filling session for note generation and related processingAudio streaming for ambient and form filling sessions
GET /ws/transcribeStream PCM_S16LE audio into a dictation (transcription) session for real-time textStream audio to dictation session
Use the same base host for REST and WebSocket calls in a given environment (for example staging https://sdp.suki-stage.com and wss://sdp.suki-stage.com). Your partnership team confirms which host and credentials apply.

Ambient Streaming

Stream PCM audio into an ambient session for note generation and related processing. Use this endpoint when you already have an ambient session and want to push live audio for that session.

Dictation Streaming

Stream PCM_S16LE audio into a dictation (transcription) session for real-time text. Use this endpoint when you have a dictation session and want to push audio for that session.
Do not send raw audio as binary WebSocket frames on /ws/stream. On /ws/transcribe, outbound audio is also sent as JSON text frames with Base64 payloads, not raw binary PCM frames.

Side-by-side comparison

TopicAmbient StreamingDictation Streaming
EndpointGET /ws/streamGET /ws/transcribe
Browser Sec-WebSocket-ProtocolSukiAmbientAuth,<ambient_session_id>,<sdp_suki_token>SukiAmbientAuth,<sdp_suki_token>,<transcription_session_id>
Non-browser headerssdp_suki_token, ambient_session_idsdp_suki_token, transcription_session_id
Audio field namedata (Base64 PCM)audioData (Base64 PCM_S16LE)
Start-of-streamSTART_TIME required firstNo START_TIME in the dictation contract documented here
End-of-streamAUDIO with data: RU9G (Base64 of bytes EOF)EVENT with event: AUDIO_END
Control messagestype: EVENT, event: enum (see FAQ)EVENT / AUDIO_END for end of audio

Next steps

Audio Streaming API Reference

Learn more about streaming audio to an ambient session.

Dictation Streaming API Reference

Learn more about streaming audio to a dictation session.

Audio Capture & Streaming FAQs

Learn more about the audio capture and streaming FAQ.
Last modified on May 22, 2026