Files
glados-ladosp-tts/HOMEASSISTANT_INTEGRATION.md
xerotacovix 4ddf29aeb7
All checks were successful
Build and Publish Docker Images / build-cuda (push) Successful in 6m12s
Build and Publish Docker Images / build-rocm (push) Successful in 6m33s
Build and Publish Docker Images / build-cpu (push) Successful in 18m51s
fixed a lot of things and actually got it to work
2026-06-13 09:56:48 +00:00

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