mirror of
https://github.com/Purple-Horizons/openclaw-voice.git
synced 2026-08-14 00:58:01 +00:00
gianni-dalerta
fe337abc7b
- ElevenLabs as primary TTS when API key available - Falls back to Chatterbox/XTTS/mock - Uses Jessica voice (cgSgspJ2msm6clMCkdW9) - 24kHz PCM output to match server expectation - Updated tests to recognize elevenlabs backend All 30 tests passing.
44 lines
685 B
Plaintext
44 lines
685 B
Plaintext
# Core
|
|
fastapi>=0.109.0
|
|
uvicorn[standard]>=0.27.0
|
|
websockets>=12.0
|
|
pydantic>=2.5.0
|
|
pydantic-settings>=2.1.0
|
|
python-multipart>=0.0.6
|
|
|
|
# Audio processing
|
|
numpy>=1.26.0
|
|
soundfile>=0.12.1
|
|
librosa>=0.10.1
|
|
webrtcvad>=2.0.10
|
|
|
|
# Speech-to-Text
|
|
openai-whisper>=20231117
|
|
faster-whisper>=1.0.0
|
|
# whisper.cpp via ctypes (optional, for CPU)
|
|
|
|
# Text-to-Speech
|
|
# chatterbox-tts # Install from source for now
|
|
torch>=2.1.0
|
|
torchaudio>=2.1.0
|
|
transformers>=4.36.0
|
|
|
|
# Voice Activity Detection
|
|
silero-vad>=4.0.0
|
|
|
|
# AI Backend
|
|
openai>=1.6.0
|
|
httpx>=0.26.0
|
|
|
|
# Utilities
|
|
pyyaml>=6.0.1
|
|
python-dotenv>=1.0.0
|
|
loguru>=0.7.2
|
|
|
|
# Dev
|
|
pytest>=7.4.0
|
|
pytest-asyncio>=0.23.0
|
|
black>=23.12.0
|
|
ruff>=0.1.0
|
|
elevenlabs>=1.0.0
|