Voice

Paseo has first-class voice support for dictation and voice mode conversations with your coding environment.

Philosophy

Dictation defaults to Grok speech-to-text, using the same xAI key as the agent. Everything else is local-first: voice mode runs speech fully on-device by default, and you can put dictation back on-device too. OpenAI is available for every speech slot. For voice reasoning/orchestration, Paseo reuses agent providers already installed and authenticated on your machine.

This keeps credentials and execution in your environment and avoids introducing a separate cloud-only voice stack.

Architecture

Speech I/O: STT and TTS providers per feature (local, xai, or openai)
Local speech runtime: ONNX models executed on CPU by default
Voice LLM orchestration: hidden agent session using your configured provider (claude, codex, or opencode)
Tooling path: MCP stdio bridge for voice tools and agent control

Local Speech

Local speech defaults to model IDs parakeet-tdt-0.6b-v2-int8 (STT) and kokoro-en-v0_19 (TTS, speaker 0 / voice 00).

Missing models are downloaded at daemon startup into $PASEO_HOME/models/local-speech. Downloads happen only for missing files.

Local STT models and language support

Model ID	Languages
`parakeet-tdt-0.6b-v2-int8`	English only (default). Includes punctuation and capitalization.
`parakeet-tdt-0.6b-v3-int8`	25 European languages, auto-detected: Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, Ukrainian.

To use a non-English language, switch the local STT model to parakeet-tdt-0.6b-v3-int8. v3 detects the spoken language automatically — there is no per-language setting for it. The language field below does not steer the local Parakeet model (v2 is English-only, v3 auto-detects); it only applies to the OpenAI STT provider.

{
  "version": 1,
  "features": {
    "dictation": {
      "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v2-int8", "language": "en" }
    },
    "voiceMode": {
      "llm": { "provider": "claude", "model": "haiku" },
      "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v2-int8", "language": "en" },
      "tts": { "provider": "local", "model": "kokoro-en-v0_19", "speakerId": 0 }
    }
  },
  "providers": {
    "local": {
      "modelsDir": "~/.paseo/models/local-speech"
    }
  }
}

For multilingual local dictation, set the model to v3 — it auto-detects the language, so no language field is needed:

{
  "version": 1,
  "features": {
    "dictation": {
      "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8" }
    }
  }
}

The language field applies to the cloud STT providers: set features.dictation.stt.language for dictation and features.voiceMode.stt.language for voice mode. If voice language is omitted, Paseo uses the dictation language before falling back to en. It has no effect on the local Parakeet models.

Grok (xAI) Speech-to-Text

Dictation uses Grok STT by default. It needs no configuration beyond an xAI API key, which it reads from the key you enter for the Grok agent provider in Settings — one key covers the agent and the mic. XAI_API_KEY in the daemon's environment works too, and XAI_STT_API_KEY overrides it for speech only.

The daemon resolves speech credentials once at startup, so a key pasted into Settings while the daemon is running takes effect on the next restart.

Grok STT posts a 16 kHz mono WAV to /v1/stt under XAI_STT_BASE_URL (default https://api.x.ai/v1). The endpoint takes no model ID — there is one Grok STT model — so features.dictation.stt.model is ignored for this provider. language is sent and also enables inverse text normalization, which is what turns spoken numbers and currency into written form.

To put dictation back on-device, set the provider explicitly:

{
  "version": 1,
  "features": {
    "dictation": {
      "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v2-int8" }
    }
  }
}

Voice mode STT can also run on xai, but voice mode additionally needs turn detection and TTS, which xAI does not provide here — those stay on local or openai.

OpenAI Voice Option

You can switch dictation, voice STT, and voice TTS to OpenAI by setting provider fields to openai and providing OpenAI credentials.

{
  "version": 1,
  "features": {
    "dictation": { "stt": { "provider": "openai" } },
    "voiceMode": {
      "stt": { "provider": "openai" },
      "tts": { "provider": "openai" }
    }
  },
  "providers": {
    "openai": {
      "stt": {
        "apiKey": "...",
        "baseUrl": "https://api.openai.com/v1"
      },
      "tts": {
        "apiKey": "...",
        "baseUrl": "https://api.openai.com/v1"
      }
    }
  }
}

providers.openai.stt covers dictation and voice mode speech-to-text, and providers.openai.tts covers voice mode text-to-speech. Because they resolve independently, you can point STT and TTS at different endpoints. Each falls back to providers.openai.apiKey/baseUrl, then OPENAI_API_KEY/OPENAI_BASE_URL, when unset. These settings configure only Paseo OpenAI speech traffic, without changing Codex or other OpenAI-backed tools.

Paseo uses these paths under the configured OpenAI base URL:

dictation STT: /v1/audio/transcriptions
voice mode STT: /v1/audio/transcriptions
voice mode TTS: /v1/audio/speech

Environment Variables

PASEO_VOICE_LLM_PROVIDER, voice agent provider override
PASEO_DICTATION_STT_PROVIDER, PASEO_VOICE_STT_PROVIDER, PASEO_VOICE_TTS_PROVIDER, speech provider selection (local, xai, or openai)
XAI_API_KEY, xAI key for Grok speech-to-text; falls back to the Grok agent provider key saved in Settings
XAI_STT_API_KEY, XAI_STT_BASE_URL, override the xAI key and base URL for speech only
OPENAI_STT_API_KEY, OPENAI_STT_BASE_URL, OpenAI speech-to-text endpoint (dictation + voice mode STT)
OPENAI_TTS_API_KEY, OPENAI_TTS_BASE_URL, OpenAI text-to-speech endpoint (voice mode TTS)
PASEO_LOCAL_MODELS_DIR, local model storage directory
PASEO_DICTATION_LOCAL_STT_MODEL, local dictation STT model ID
PASEO_VOICE_LOCAL_STT_MODEL, PASEO_VOICE_LOCAL_TTS_MODEL, local voice STT/TTS model IDs
PASEO_DICTATION_LANGUAGE, dictation STT language (cloud STT only; ignored by local Parakeet)
PASEO_VOICE_LANGUAGE, voice mode STT language; falls back to PASEO_DICTATION_LANGUAGE when unset (cloud STT only; ignored by local Parakeet)
PASEO_VOICE_LOCAL_TTS_SPEAKER_ID, PASEO_VOICE_LOCAL_TTS_SPEED, optional local voice TTS tuning

Operational Notes

Voice mode can launch and control agents. Treat voice prompts with the same care as direct agent instructions, especially when specifying working directories or destructive operations.

#Voice

#Philosophy

#Architecture

#Local Speech

#Local STT models and language support

#Grok (xAI) Speech-to-Text

#OpenAI Voice Option

#Environment Variables

#Operational Notes