VoiceThere
Sign up

Cartesia TTS on VoiceThere

Cartesia Sonic TTS over WebSocket on VoiceThere cloud. Pair with a separate STT vendor. AGENT_CARTESIA_API_KEY.

Overview of all vendors: STT & TTS vendors.

What it is

Cartesia provides low-latency TTS over WebSocket. VoiceThere does not run Cartesia STT; pair Cartesia TTS with another vendor for transcription.

Home: Cartesia docs

Set up on VoiceThere

  • Dashboard: Project Settings → Voice (STT / TTS). Pick cartesia on the leg this vendor supports. Add project secrets from the list below, then Deploy to cloud.
  • Secrets: Store keys as AGENT_* project secrets (see Agent environment & secrets).
  • API: Patch stt_provider / tts_provider on the project before deploy. See Control plane API.

Project secrets for this vendor

  • AGENT_CARTESIA_API_KEY: Cartesia API key. TTS synthesis on the runner.

Optional env fields

  • AGENT_CARTESIA_VOICE_ID: Voice id. Cartesia voice id.

CLI (after secrets exist):

voicethere projects voice set --project YOUR_PROJECT_ID \
  --stt-provider openai --tts-provider cartesia \
  --tts-model sonic-3 --tts-voice YOUR_VOICE_ID

Models and voices you can pick

Project Voice settings in the dashboard lists every model and voice id VoiceThere accepts for this vendor. The same allowlists ship in the npm package @node-webrtc-rust/voice-catalog (pinned on your platform release).

TTS model examples: sonic-3, sonic-3.6

Optional AGENT_CARTESIA_VOICE_ID sets the Cartesia voice id.

What the implementation does

The runner opens Cartesia WebSocket TTS for Sonic family models and streams audio back to the session. Progressive TTS chunks depend on the model and Cartesia response mode.

Limitations

  • TTS-only on VoiceThere. You must configure a separate STT provider.
  • Billed by Cartesia.

Official docs

← All documentation