DeepInfra

Use DeepInfra's hosted TTS models as your provider.

Setup

In Settings → Admin → Providers:

1. Add a provider with type Deepinfra.
2. Keep base URL as https://api.deepinfra.com/v1/openai.
3. Enter your API key.
4. Set your preferred default model/voice.

Or seed it on first boot (see Seed a provider from the environment):

API_BASE=https://api.deepinfra.com/v1/openai
API_KEY=your-deepinfra-key

Users choose the provider, model and voice in Settings → Model & Voice.

Notes

• Available models include hexgrad/Kokoro-82M and canopylabs/orpheus-3b-0.1-ft.
• Without an API key, only the free-tier model (hexgrad/Kokoro-82M) is shown in the dropdown.
• Speech is requested by the compute worker, not the browser. The API key is never sent to browsers.

References

• DeepInfra TTS models
• TTS Providers
• TTS Environment Variables