VoiceThere
Sign up

Groq speech on VoiceThere

Groq Whisper file STT and Orpheus TTS on VoiceThere cloud with AGENT_GROQ_API_KEY. No live STT partials.

Overview of all vendors: STT & TTS vendors.

What it is

Groq hosts Whisper-class STT and Orpheus TTS models with fast inference. VoiceThere uses file upload STT and full-body HTTP TTS on Groq.

Home: Groq speech to text

Set up on VoiceThere

  • Dashboard: Project Settings → Voice (STT / TTS). Pick groq 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_GROQ_API_KEY: Groq API key. Groq STT and TTS on the runner.

CLI (after secrets exist):

voicethere projects voice set --project YOUR_PROJECT_ID \
  --stt-provider groq --tts-provider groq \
  --stt-model whisper-large-v3-turbo \
  --tts-model canopylabs/orpheus-v1-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: whisper-large-v3-turbo, whisper-large-v3

TTS model examples: canopylabs/orpheus-v1-english, canopylabs/orpheus-arabic-saudi

TTS voice examples: troy, autumn

What the implementation does

STT sends each utterance as a multipart file upload to Groq Whisper models. There is no live socket and no user_speech_partial events from this path. Orpheus TTS returns a complete audio body per request.

Limitations

  • No live STT partials. Barge-in tuning that depends on partials will not see Groq STT partials.
  • Billed by Groq.

Official docs

← All documentation