openreader/docs-site/versioned_docs/version-v4.3.0/configure/tts-provider-guides/openai.md
github-actions[bot] 2b27c16367
Some checks failed
Docs Deploy / build (push) Has been cancelled
Playwright Tests / e2e-testing (push) Has been cancelled
Vitest Tests / vitest-testing (push) Has been cancelled
Docs Deploy / deploy (push) Has been cancelled
docs: snapshot v4.3.0
2026-06-13 21:27:08 +00:00

1.1 KiB

title
OpenAI

Use the OpenAI TTS API as your provider.

Setup

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

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

Legacy bootstrap seed (optional, first boot only):

API_BASE=https://api.openai.com/v1
API_KEY=sk-...

Per-user Settings → TTS Provider (only when restrictUserApiKeys=false):

  1. Set provider to OpenAI.
  2. The base URL is pre-filled, no changes needed.
  3. Enter your API_KEY.
  4. Choose a model and voice.

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

Notes

  • Models: tts-1, tts-1-hd, gpt-4o-mini-tts
  • TTS requests are sent from the server, not the browser. The API key is never exposed to clients.

References