Tags

Tags give the ability to mark specific points in history as being important

  • v2.0.1

    3b76a92d · fix: add NVIDIA_VISIBLE_DEVICES=all for GPU access without resource requests ·

  • v2.0.0

    4a1841de · Merge dev into master: Silero TTS v2.0.0 · 
    v2.0.0: Silero TTS — production-ready multilingual TTS

Replaced XTTS-v2 with Silero Models:
- 50+ speakers across 15+ languages (Kazakh, Russian, English, Tatar, Uzbek, etc.)
- GPU-accelerated: ~108 req/s, <50ms avg latency
- Auto-chunking: texts up to 10000 chars split by sentences automatically
- Async inference lock for thread safety
- Input validation (speaker, sample_rate, speed, text length)
- Generation timeout (504 on exceed)
- Optional API Key auth (Bearer token)
- OpenAI-compatible API (/v1/audio/speech)
- Pinned dependencies and Silero hub version
- Health check endpoint

  • v1.0.0

    519b87c9 · fix: replace deprecated gpu= with tts.to(device) · 
    v1.0.0 - OpenAI-compatible TTS server with XTTS-v2

Features:
- POST /v1/audio/speech (OpenAI-compatible)
- GET /v1/models, /v1/voices, /health
- Authorization via API_KEY env (optional)
- model=text-to-speech required
- Default voice embedded in image
- GPU auto-detection (CUDA)
- LiteLLM proxy compatible
- Port 8000