Telnyx Meeting Bot Now Available in Beta

5, Aug 2026

Telnyx Meeting Bot is now available in beta. Developers can programmatically add a Telnyx-controlled AI participant to a Zoom, Google Meet, Microsoft Teams, or Webex meeting, and receive live transcription, in-meeting speech and chat, and structured post-meeting artifacts through one REST API contract.

What's new

  • Meeting Bot API: The 15 operations on /v2/meeting_sessions let you create a session for an existing meeting, poll status, update or cancel a scheduled session, drive in-meeting actions, read the live transcript and events, retrieve recordings, and request post-meeting artifacts.
  • Live transcription with Telnyx STT: Meeting audio is streamed into Telnyx STT, with Nova-3 as the default model, and the transcript is available live through long-poll on GET /v2/meeting_sessions/{id}/transcript and through lifecycle events.
  • Programmable bot speech and chat: actions/speak runs text through Telnyx TTS and plays it into the meeting, actions/stop_speaking interrupts, and actions/send_chat posts a chat message. barge_in stops bot audio when a human speaks.
  • Post-meeting artifacts via Telnyx Inference: Request summary and action_items artifacts asynchronously. summarize_on_end auto-generates a summary once the final transcript settles, delivered through the artifact.completed webhook when a webhook URL is set.
  • Recording retrieval: GET /v2/meeting_sessions/{id}/recordings returns pass-through download URLs for recordings captured during the meeting.
  • Optional webhooks: Set webhook_url on session create to receive signed meeting lifecycle events. Outbound webhooks are off by default.
  • Search across meetings: Add transcripts as sources to a Telnyx AI Search collection and query across all past meetings for scored, citation-ready results.
  • Account-scoped tenancy: Every operation authenticates with a Telnyx API key at the gateway and is scoped to the authenticated account. Foreign and missing IDs both return 404.
  • Metering: Transcription at $0.015/min (Telnyx STT rate) plus bot presence at $0.012/min, billed per minute the bot is in the meeting. STT, TTS, and Inference are billed through the customer's Telnyx API key.

Why it matters

  • Agents have been shut out of meetings. A meeting is where decisions happen, but until now an agent could not join one, hear what was said, or contribute. Meeting Bot gives an agent live and durable meeting context through the same API key it already uses for calls, STT, TTS, and inference.
  • Granola and similar tools record meetings for humans. Meeting Bot is for agents. A developer can send an agent into a standup it cannot attend, stream the transcript back, raise a prompt through speech, and retain the full meeting context afterwards.
  • Meeting platforms each ship their own recorder, transcription, and bot APIs with different contracts and rate limits. Meeting Bot abstracts that behind one Telnyx-shaped REST contract, so the agent does not learn four vendor SDKs.
  • STT, TTS, and Inference stay on Telnyx primitives, so audio and inference stay on Telnyx infrastructure. The meeting-presence adapter is swappable, so the provider seam can change later without touching the customer contract.
  • One API key, one bill, one dashboard. No second vendor for meeting presence, no second contract for transcription, no integration tax at every API change.

Example use cases

  • An engineering team brings its agent into a technical brainstorming session so it retains the discussion and can contribute when instructed.
  • A user sends a bot to a standup they cannot attend. The bot streams the transcript back, raises a prompt through speech, and returns the meeting context afterwards.
  • A support team records every escalation call through a consistent Telnyx pipeline, then generates action items and a summary through Telnyx Inference.
  • A sales team pipes meeting transcripts into their CRM workflow, with the bot joining Zoom, Webex, Teams, or Meet and returning a structured artifact.
  • A developer building a meeting-aware agent uses the same Telnyx API key for meeting presence, STT, TTS, and inference, with no per-platform bot SDK in the stack.

Getting started

  1. Get a Telnyx API key from Mission Control.
  2. Create a meeting session with POST https://api.telnyx.com/v2/meeting_sessions, passing meeting_url, bot_name, and optional webhook_url, summarize_on_end, voice, barge_in, metadata, and idempotency_key.
  3. Poll GET /v2/meeting_sessions/{id} until the status is active. If the platform requests admission, admit the bot named in bot_name inside the meeting UI.
  4. Read the live transcript with GET /v2/meeting_sessions/{id}/transcript?after=0&limit=100.
  5. Make the bot speak with POST /v2/meeting_sessions/{id}/actions/speak, send a chat message with actions/send_chat, or stop speech with actions/stop_speaking.
  6. After the meeting ends, retrieve recordings with GET /v2/meeting_sessions/{id}/recordings, or request a summary or action_items artifact with POST /v2/meeting_sessions/{id}/artifacts.

Learn more in the Telnyx API reference or the Telnyx developer docs.