Add a dedicated Admin Panel documentation page detailing management of shared TTS providers and site features via the admin UI. Update all TTS provider guides, environment variable references, and deployment docs to clarify the new runtime configuration model: environment variables serve as first-boot seeds only, with ongoing management handled through the admin interface. Revise sidebars and cross-links to include the new admin panel docs and clarify the distinction between legacy env-based and admin-managed configuration.
1.6 KiB
1.6 KiB
| title |
|---|
| Replicate |
Use Replicate's hosted TTS models as your provider.
Setup
Recommended (auth + admin): Settings → Admin → Shared providers
- Add a shared provider with type
replicate. - Enter your API key.
- Set default model to:
alphanumericuser/kokoro-82m:89b6fa84e4fa2dd6bd3a96be3e1f12827a3516c9fda8fddbac7a0be131c9a6f5(or your preferred model).
Legacy bootstrap seed (optional, first boot only):
API_KEY=r8_...
NEXT_PUBLIC_DEFAULT_TTS_MODEL=alphanumericuser/kokoro-82m:89b6fa84e4fa2dd6bd3a96be3e1f12827a3516c9fda8fddbac7a0be131c9a6f5
Per-user Settings → TTS Provider (only when restrictUserApiKeys=false):
- Set provider to
Replicate. - Enter your
API_KEY. - Choose a model and voice.
See TTS Providers for admin-shared vs per-user behavior.
Notes
- Built-in Replicate models:
alphanumericuser/kokoro-82m:89b6fa84e4fa2dd6bd3a96be3e1f12827a3516c9fda8fddbac7a0be131c9a6f5google/gemini-3.1-flash-ttsminimax/speech-2.8-turboqwen/qwen3-ttsinworld/tts-1.5-mini
- You can also choose
Otherand enter any Replicate model ID (for exampleowner/model-nameorowner/model-name:version). - Native model speed is not available on all Replicate models; OpenReader hides/disables native speed controls where unsupported.
- TTS requests are sent from the server, not the browser. The API key is never exposed to clients.