Voice | AMADEV Documentation

Amadev Getting started Why Amadev? Providers Supported providers Custom providers CLI Amadev MCP Git worktrees Schedules Skills Voice Configuration Security Best practices Amadev Getting started Why Amadev? Providers Supported providers Custom providers CLI Amadev MCP Git worktrees Schedules Skills Voice Configuration Security Best practices

# Amadev has first-class voice support for dictation and realtime conversations with your coding environment.

#Philosophy

# Voice is local-first. You can run speech fully on-device, or choose OpenAI for speech features. For voice reasoning/orchestration, Amadev 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 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

Code

local

Code

openai

Code

claude

Code

codex

Code

opencode

#Local Speech

# Local speech defaults to model IDs parakeet-tdt-0.6b-v3-int8 (STT) and kokoro-en-v0_19 (TTS, speaker 0 / voice 00).

Code

parakeet-tdt-0.6b-v3-int8

Code

kokoro-en-v0_19

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

Code

$AMADEV_HOME/models/local-speech

Code

{ "version": 1, "features": { "dictation": { "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8" } }, "voiceMode": { "llm": { "provider": "claude", "model": "haiku" }, "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8" }, "tts": { "provider": "local", "model": "kokoro-en-v0_19", "speakerId": 0 } } }, "providers": { "local": { "modelsDir": "~/.amadev/models/local-speech" } } }

Code

{ "version": 1, "features": { "dictation": { "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8" } }, "voiceMode": { "llm": { "provider": "claude", "model": "haiku" }, "stt": { "provider": "local", "model": "parakeet-tdt-0.6b-v3-int8" }, "tts": { "provider": "local", "model": "kokoro-en-v0_19", "speakerId": 0 } } }, "providers": { "local": { "modelsDir": "~/.amadev/models/local-speech" } } }

#OpenAI Speech Option

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

Code

openai

Code

OPENAI_API_KEY

Code

{ "version": 1, "features": { "dictation": { "stt": { "provider": "openai" } }, "voiceMode": { "stt": { "provider": "openai" }, "tts": { "provider": "openai" } } }, "providers": { "openai": { "apiKey": "..." } } }

Code

{ "version": 1, "features": { "dictation": { "stt": { "provider": "openai" } }, "voiceMode": { "stt": { "provider": "openai" }, "tts": { "provider": "openai" } } }, "providers": { "openai": { "apiKey": "..." } } }

#Environment Variables

OPENAI_API_KEY, OpenAI speech credentials
AMADEV_VOICE_LLM_PROVIDER, voice agent provider override
AMADEV_LOCAL_MODELS_DIR, local model storage directory
AMADEV_DICTATION_LOCAL_STT_MODEL, local dictation STT model ID
AMADEV_VOICE_LOCAL_STT_MODEL, AMADEV_VOICE_LOCAL_TTS_MODEL, local voice STT/TTS model IDs
AMADEV_VOICE_LOCAL_TTS_SPEAKER_ID, AMADEV_VOICE_LOCAL_TTS_SPEED, optional local voice TTS tuning

Code

OPENAI_API_KEY

Code

AMADEV_VOICE_LLM_PROVIDER

Code

AMADEV_LOCAL_MODELS_DIR

Code

AMADEV_DICTATION_LOCAL_STT_MODEL

Code

AMADEV_VOICE_LOCAL_STT_MODEL

Code

AMADEV_VOICE_LOCAL_TTS_MODEL

Code

AMADEV_VOICE_LOCAL_TTS_SPEAKER_ID

Code

AMADEV_VOICE_LOCAL_TTS_SPEED

#Operational Notes

# Realtime voice can launch and control agents. Treat voice prompts with the same care as direct agent instructions, especially when specifying working directories or destructive operations. View this page on GitHub