49 lines
1.6 KiB
Markdown
49 lines
1.6 KiB
Markdown
# Home Assistant GLaDOS TTS Integration Guide
|
|
|
|
This server uses the [Wyoming protocol](https://www.home-assistant.io/integrations/wyoming/) for TTS, which is natively supported by Home Assistant.
|
|
|
|
## Adding to Home Assistant
|
|
|
|
### Option 1: Wyoming Integration (Recommended)
|
|
|
|
Home Assistant has a built-in Wyoming integration that auto-discovers Wyoming servers on the network.
|
|
|
|
1. Go to **Settings > Devices & Services > Add Integration**
|
|
2. Search for **Wyoming** and select it
|
|
3. If the server is on the same host as Home Assistant, use `localhost` with the appropriate port:
|
|
- CUDA: `10200`
|
|
- CPU: `10201`
|
|
- ROCm: `10202`
|
|
4. If running on a different machine, use the server's IP address
|
|
|
|
### Option 2: Manual configuration.yaml
|
|
|
|
```yaml
|
|
# Wyoming protocol TTS
|
|
wyoming:
|
|
- host: 192.168.1.100 # Replace with your server IP
|
|
port: 10200 # 10200=CUDA, 10201=CPU, 10202=ROCm
|
|
```
|
|
|
|
## Port Reference
|
|
|
|
| Variant | Container Port | Host Port |
|
|
|---------|---------------|-----------|
|
|
| CUDA | 10200 | 10200 |
|
|
| CPU | 10200 | 10201 |
|
|
| ROCm | 10200 | 10202 |
|
|
|
|
## Voice Configuration
|
|
|
|
The server exposes a single voice:
|
|
- **Name**: `glados`
|
|
- **Languages**: English (`en`), Japanese (`ja`), Chinese (`zh`)
|
|
- Language is auto-detected from input text
|
|
|
|
## Troubleshooting
|
|
|
|
- Ensure the container is running: `docker compose ps`
|
|
- Check logs: `docker compose logs glados-tts-cuda` (or cpu/rocm)
|
|
- The model downloads automatically on first start; this may take several minutes
|
|
- Verify network connectivity between Home Assistant and the TTS server
|