Every sample on every page follows this. Change it any time.

Get a test key
BashBrainTeammatesPricingDevelopersGet a test key

talk

Start a live voice call between one of your users and Bash. Create a session (a short-lived link for that user), open its url, and the page joins the call. Everything said in the call is saved to the same conversation as text.

Ask something first

The call below joins this conversation.

TypeScript
const traveller = vestra.user('traveller-42');const run = traveller.ask('Find me a flight to Goa on Friday.');await run.text();

Call in an existing conversation

Open call.url, and the page joins the call.

TypeScript
const call = await traveller.talk({ conversation: run.conversation! });console.log(call.url);

Start a new conversation by voice

TypeScript
const fresh = await traveller.talk();await fresh.end();

Ask something first

The call below joins this conversation.

Python
traveller = vestra.user("traveller-42")run = traveller.ask("Find me a flight to Goa on Friday.")run.text()

Call in an existing conversation

Open call.url, and the page joins the call.

Python
call = traveller.talk(conversation=run.conversation)print(call.url)

Start a new conversation by voice

Python
fresh = traveller.talk()fresh.end()

Call in an existing conversation

You get a link, and what is said is saved to that conversation.

CLI
vestra talk --user traveller-42 --conversation conv_8f2k

Call in an existing conversation

Open the session's url, and the page joins the call.

HTTP
curl "$VESTRA_BASE_URL/v1/sessions" \  -H "Authorization: Bearer $VESTRA_API_KEY" \  -H "Content-Type: application/json" \  -d '{ "user_id": "traveller-42", "conversation_id": "conv_8f2k", "voice": true }'

Connect your own voice client

The session's page does this for you: it sends the browser's WebRTC offer with the session's own token, and gets the answer back. Call it yourself only if you build your own client.

HTTP
curl "$VESTRA_BASE_URL/v1/sessions/ses_8h2/voice" \  -H "Authorization: Bearer $SESSION_TOKEN" \  -H "Content-Type: application/json" \  -d '{ "sdp": "the WebRTC offer from the browser" }'
MCP
{  "method": "tools/call",  "params": {    "name": "talk",    "arguments": { "user": "traveller-42", "conversation": "conv_8f2k" }  }}

Good to know

When the call ends

The session.ended event carries the call's length in seconds, and its transcript.

Which setup answers the call

Bash answers with the conversation's deployment, which is your agent's setup. If the conversation has none, it uses the user's default deployment, and then your company's.

Building your own voice client

The session's page sends the browser's WebRTC offer to POST /v1/sessions/{id}/voice with the session's token. Call this route yourself only if you build your own voice client. Vestra accepts calls only from its own page and from your allowed origins.

The routes behind talk1 route, each with every field in the API reference
POST/v1/sessions/{session_id}/voiceCalled from the user's browser with the session's token and its WebRTC offer; answers the model's answer. Audio then flows straight to the voice model, and everything said lands in the session's conversation. For a session opened with voice.