Russell Ballestrini
d48fa6b29c
- Added kokoro>=0.9.2 and soundfile to requirements.txt - Created kokoro_wrapper class for 24kHz decoder-only TTS - Added tts-1-kokoro endpoint with full voice mapping - Mapped 32 Kokoro voices (11 female American, 9 male American, 4 female British, 4 male British, 4 Spanish, etc.) - Added OpenAI-compatible aliases (alloy, echo, fable, onyx, nova, shimmer) - Lightweight 82M parameter model, Apache licensed Voices: - American English (lang_code 'a'): 20 voices - British English (lang_code 'b'): 8 voices - Supports 9 languages total (a, b, e, f, h, i, j, p, z) 🦝 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
38 lines
1.7 KiB
Text
38 lines
1.7 KiB
Text
fastapi
|
|
uvicorn
|
|
loguru
|
|
# OHF-Voice fork doesn't have installable Python package yet
|
|
# Stick with PyPI piper-tts but use absolute paths in config
|
|
piper-tts>=1.2.0
|
|
# 🦝 RACCOON TODO: Create our own PyPI package from OHF-Voice fork
|
|
# git+https://github.com/OHF-Voice/piper1-gpl.git@v1.3.0#subdirectory=src/python_run
|
|
coqui-tts[languages]
|
|
# Silero TTS - actively maintained, small efficient models
|
|
# Note: Silero models are loaded via torch.hub, no package install needed
|
|
# Models: ~50-100MB each, CPU-friendly, real-time capable
|
|
omegaconf # Required by Silero TTS
|
|
# Chatterbox - emotion control, 23 languages (Resemble AI)
|
|
# Install from git since no PyPI package exists yet
|
|
# 🦝 RACCOON NOTE: Disabled due to dependency conflict with Coqui TTS
|
|
# gradio 5.44.1 requires typer<1.0 and >=0.12, but spacy 3.6.x requires typer<0.10.0
|
|
# TODO: Test Chatterbox in isolated environment or wait for dependency updates
|
|
# git+https://github.com/resemble-ai/chatterbox.git
|
|
langdetect
|
|
pyyaml
|
|
# Kokoro TTS - fast decoder-only architecture
|
|
# Lightweight decoder-only TTS, 82M params, 24kHz output
|
|
kokoro>=0.9.2
|
|
soundfile # Required by Kokoro for audio output
|
|
transformers>=4.35.0
|
|
# Hugging Face Hub for model downloads
|
|
huggingface-hub[cli]
|
|
# Creating an environment where deepspeed works is complex, for now it will be disabled by default.
|
|
#deepspeed
|
|
|
|
torch; sys_platform != "darwin"
|
|
torchaudio; sys_platform != "darwin"
|
|
# for MPS accelerated torch on Mac - doesn't work yet, incomplete support in torch and torchaudio
|
|
torch; --index-url https://download.pytorch.org/whl/cpu; sys_platform == "darwin"
|
|
torchaudio; --index-url https://download.pytorch.org/whl/cpu; sys_platform == "darwin"
|
|
|
|
# ROCM (Linux only) - use requirements.amd.txt
|