Skip to main content
WSS
assistant_id
type:string
required

Identifier of the AI Assistant to converse with.

bearerAuth
type:http

Telnyx API v2 Bearer token authentication.

query
type:object

Query parameters passed when opening the WebSocket connection.

Input Audio Append Frame
type:object

Client-to-Telnyx frame carrying a chunk of microphone audio. The audio field is a base64-encoded PCM16 payload at the sample rate requested with the input_sample_rate query parameter. Frames larger than 1 MiB are rejected with a frame_too_large error.

Session Created Frame
type:object

First frame sent by Telnyx once the conversation has started. Confirms the session and the negotiated input and output audio formats.

Speech Started Frame
type:object

Sent when server-side voice-activity detection determines the user has started speaking. Edge-triggered.

Speech Stopped Frame
type:object

Sent when server-side voice-activity detection determines the user has stopped speaking. Edge-triggered, and never sent without a preceding speech-started.

Input Transcription Completed Frame
type:object

Transcript of the audio the user streamed for the current turn.

Response Created Frame
type:object

Marks the start of an assistant turn. The response.id correlates the audio and transcript deltas that follow.

Response Audio Delta Frame
type:object

A chunk of the assistant''s synthesized speech, as base64-encoded PCM16 at the output rate announced in session.created.

Response Audio Transcript Delta Frame
type:object

A chunk of the text transcript of the assistant''s spoken response, streamed alongside the audio deltas.

Response Audio Done Frame
type:object

Sent when the assistant has finished streaming audio for the turn.

Response Done Frame
type:object

Marks the end of an assistant turn, including its final status.

Error Frame
type:object

Sent when an error occurs. Some errors are non-fatal and leave the session open; others close the connection after the frame is sent.