danvics/openreader
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
openreader/docs-site/docs/configure/tts-provider-guides/other.md
Richard R 34b94534cf docs(tts): clarify fallback voice set logic for OpenAI-compatible providers 
Update documentation to specify that OpenReader uses the Kokoro voice set
for Kokoro models and the standard OpenAI voices for other models when no
voice listing endpoint is available. Improves clarity on provider fallback
behavior.
2026-06-09 11:00:51 -06:00

2.3 KiB
Raw Permalink Blame History

title
Other

Use any OpenAI-compatible TTS service with OpenReader, including self-hosted servers not covered by a dedicated guide.

Requirements

Your service only needs an OpenAI-compatible speech endpoint:

  • POST /v1/audio/speech — required.
  • Voice listing is optional and auto-discovered from /v1/audio/voices, /v1/voices, or /v1/styles. If none respond, OpenReader falls back to default voices — the Kokoro voice set for Kokoro models, otherwise the standard OpenAI voices (alloy, echo, fable, onyx, nova, shimmer).

The endpoint may return mp3, wav, ogg, or flac — OpenReader normalizes non-mp3 audio to mp3 automatically. An API key is optional.

Known compatible implementations: Kokoro-FastAPI, KittenTTS-FastAPI, Orpheus-FastAPI, Supertonic.

Setup

Recommended (auth + admin): Settings → Admin → Shared providers

  1. Add a shared provider with type custom-openai.
  2. Set API_BASE to your service base URL (typically ending in /v1).
  3. Set API key if your service requires authentication.
  4. Set a default model/voice supported by your backend.

Legacy bootstrap seed (optional, first boot only):

API_BASE=http://your-tts-server/v1
# API_KEY=optional-key-if-required

Or in-app via Settings → TTS Provider:

  1. Set provider to Custom OpenAI-Like.
  2. Set API_BASE to your service's base URL (typically ending in /v1).
  3. Set API_KEY if your service requires authentication.
  4. Choose a model and voice supported by your backend.

See TTS Providers for admin-shared vs per-user behavior.

:::warning TTS requests are server-side API_BASE must be reachable from the Next.js server, not just the browser. In Docker, use container names or host.docker.internal. :::

Troubleshooting

If voices don't load, confirm the server is reachable from the Next.js runtime and that at least one of /v1/audio/voices, /v1/voices, or /v1/styles returns a valid response. If none do, OpenReader falls back to default voices — synthesis still works as long as POST /v1/audio/speech succeeds.

References