---
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:

```bash
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