metadata
title: Neuapi
emoji: 👀
colorFrom: blue
colorTo: pink
sdk: docker
pinned: false
NeuTTS API on Hugging Face Spaces
OpenAI-compatible Text-to-Speech API powered by NeuTTS.
Environment Variables
| Variable | Default | Description |
|---|---|---|
NEUTTS_DEFAULT_MODELS |
neutts-nano-q4-gguf |
Comma-separated model IDs |
NEUTTS_DEFAULT_CODEC |
neuphonic/neucodec-onnx-decoder |
Codec model |
NEUTTS_DEFAULT_VOICE |
jo |
Default voice name |
NEUTTS_DEFAULT_BACKBONE_DEVICE |
cpu |
Device for backbone |
NEUTTS_DEFAULT_CODEC_DEVICE |
cpu |
Device for codec |
NEUTTS_LOG_LEVEL |
INFO |
Log level |
NEUTTS_CORS_ENABLED |
true |
Enable CORS |
API Usage
The API is OpenAI-compatible:
curl -X POST "https://{your-space}.hf.space/v1/audio/speech" \
-H "Content-Type: application/json" \
-d '{
"model": "neutts-nano-q4-gguf",
"input": "Hello, world!",
"voice": "jo",
"response_format": "mp3"
}' \
--output speech.mp3
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference