https://github.com/intelligentsandbox/tts
custom tts system
https://github.com/intelligentsandbox/tts
kokoro onnx piper text-to-speech twitch
Last synced: about 1 month ago
JSON representation
custom tts system
- Host: GitHub
- URL: https://github.com/intelligentsandbox/tts
- Owner: IntelligentSandbox
- License: gpl-2.0
- Created: 2025-06-09T02:42:43.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2026-05-11T16:44:41.000Z (about 1 month ago)
- Last Synced: 2026-05-11T18:26:56.806Z (about 1 month ago)
- Topics: kokoro, onnx, piper, text-to-speech, twitch
- Language: Python
- Homepage: http://localhost:8000/
- Size: 230 MB
- Stars: 0
- Watchers: 0
- Forks: 1
- Open Issues: 15
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TTS
A FastAPI-based service for local, high-speed neural text-to-speech synthesis. Supports Piper and Kokoro backends.
https://github.com/user-attachments/assets/d545fa6f-5a4f-4dc7-8460-3a5d0ab15ff1
## Installation
```bash
# Install system requirements
sudo apt install ffmpeg
# Install python dependencies
python3 src/setup.py
source src/tts-venv/bin/activate
```
## Usage
**Start the service:**
```bash
cd src/
python app.py
```
**Python Example:**
```python
import requests
# Generate speech with an API key
response = requests.post(
"http://localhost:8000/api/tts",
headers={"X-API-Key": "secret-key"},
json={
"text": "Hello! [SFX: airhorn] Welcome.",
"voice": "en_US-ryan-high"
}
)
# Save the audio output
with open("speech.mp3", "wb") as f:
f.write(response.content)
```