Pocket-TTS / README.md
Nymbo's picture
Update README.md
ad9ea82 verified
---
title: Pocket-TTS 100M
emoji: πŸ”Š
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 6.2.0
app_file: app.py
pinned: true
license: apache-2.0
short_description: High quality, efficient voice cloning. Just 100M parameters.
---
# Pocket-TTS
A lightweight text-to-speech application built with [kyutai/pocket-tts](https://huggingface.co/kyutai/pocket-tts) and Gradio.
## Features
- **Fast CPU inference** β€” ~6x faster than real-time on modern CPUs
- **Low latency** β€” ~200ms to first audio chunk
- **Streaming output** β€” Audio plays as it generates
- **Voice cloning** β€” Use custom voice samples (MP3, WAV, FLAC, etc.)
- **Pre-computed embeddings** β€” Voices work without voice cloning auth on HF Spaces
## Quick Start
```bash
pip install -r requirements.txt
python app.py
```
Open http://127.0.0.1:7860 in your browser.
## Adding Custom Voices
1. Drop audio files (MP3, WAV, etc.) into the `voices/` directory
2. Restart the app
3. Embeddings are created automatically on first boot (requires HF auth locally)
4. Once created, embeddings are saved to `embeddings/` and work without auth
### Structure
```
Pocket-TTS/
β”œβ”€β”€ app.py
β”œβ”€β”€ requirements.txt
β”œβ”€β”€ voices/ # Your custom voice audio files
β”‚ └── my_voice.mp3
└── embeddings/ # Auto-generated (commit these for HF Spaces)
└── my_voice.safetensors
```
## HuggingFace Spaces Deployment
**Option 1: Pre-commit embeddings (no auth needed on Space)**
1. Run the app locally first (with HF auth) to generate embeddings
2. Commit both `voices/` and `embeddings/` directories
3. The Space will use pre-computed embeddings
**Option 2: Auto-create embeddings on Space (requires valid token)**
1. Accept terms at https://huggingface.co/kyutai/pocket-tts
2. Add `HF_TOKEN` secret in Space settings (must be a valid token)
3. Embeddings are created automatically on first boot
## Model Info
- **Model**: [kyutai/pocket-tts](https://huggingface.co/kyutai/pocket-tts)
- **Parameters**: 100M
- **Language**: English only
- **Sample rate**: 24kHz
## License
See the [kyutai/pocket-tts](https://huggingface.co/kyutai/pocket-tts) model card for licensing information.