VoiceThere
Sign up

AssemblyAI STT on VoiceThere

AssemblyAI universal streaming STT on VoiceThere cloud. STT-only; pair with a TTS vendor. AGENT_ASSEMBLYAI_API_KEY.

Overview of all vendors: STT & TTS vendors.

What it is

AssemblyAI universal streaming models transcribe live audio over a WebSocket. VoiceThere uses AssemblyAI for STT only.

Home: AssemblyAI docs

Set up on VoiceThere

  • Dashboard: Project Settings → Voice (STT / TTS). Pick assemblyai 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_ASSEMBLYAI_API_KEY: AssemblyAI API key. Streaming STT on the runner.

CLI (after secrets exist):

voicethere projects voice set --project YOUR_PROJECT_ID \
  --stt-provider assemblyai --tts-provider openai \
  --stt-model universal-streaming-english

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).

STT examples: universal-streaming-english, universal-3-6-pro

What the implementation does

The runner connects to AssemblyAI streaming STT with the selected speech_model id. Partial transcripts are available on the stream.

Limitations

  • No TTS on this vendor. Pair with OpenAI, Deepgram, Cartesia, or another TTS provider.
  • Billed by AssemblyAI.

Official docs

← All documentation