Integration GuidesThird-Party Integrations
Open Notebook Setup
Add Kitta Audio OpenAI-compatible TTS credentials and a speech model to Open Notebook for podcasts and audio summaries.
Connect Kitta Audio TTS to Open Notebook
Open Notebook supports an OpenAI-compatible TTS provider for podcast generation, with separate credentials, model, and voice settings.
Add credentials
Open:
Settings → API Keys → Add Credential → OpenAI-CompatibleEnter:
| Setting | Value |
|---|---|
| TTS Base URL | https://fishaudio.org/v1 |
| API Key | Your Kitta Audio API key |
Save and run Test Connection. Then open Settings → Models → Text-to-Speech and add:
| Setting | Value |
|---|---|
| Provider | openai_compatible |
| Model Name | fishaudio-s21pro-flash |
| Display Name | Kitta Audio S2.1 Pro |
Generate a podcast
Select the new model in the podcast or audio generator and set Voice to the system test Voice ID. Replace it with your preferred voice after the first successful generation.
Troubleshooting
- Docker cannot connect: Kitta Audio uses a public HTTPS URL; do not replace it with
host.docker.internal. - Kitta Audio is missing from models: select
openai_compatibleas the provider. - Default voice fails: manually enter a Kitta Audio Voice ID.
- 401/402: verify credentials and API credits.