Fish Audio Docs
Integration GuidesThird-Party Integrations
Back to site

AnythingLLM Setup

Configure Fish Audio as an OpenAI-compatible TTS provider for spoken knowledge-base and chat responses in AnythingLLM.

Connect Fish Audio TTS to AnythingLLM

AnythingLLM supports any OpenAI-compatible TTS service. Use Fish Audio voices to read knowledge-base answers and chat responses aloud.

Configure the speech provider

Open:

Settings → AI Providers → Voice & Speech → Text-to-Speech

Select Generic OpenAI-Compatible, then enter:

SettingValue
Base URLhttps://fishaudio.org/v1
API KeyYour Fish Audio API key
Modelfishaudio-s21pro-flash
Voice00a1b221-6137-4b73-ad62-b0cbce134167

Save the provider, generate a short Workspace response, and use its speech control. After it plays, replace the test voice with your preferred Voice ID.

Troubleshooting

  • Provider cannot be saved: use a Base URL ending at /v1 and a valid API key.
  • Browser speech is still used: select Generic OpenAI-Compatible as the active TTS provider.
  • Invalid model or voice: do not use OpenAI defaults such as tts-1 or alloy.
  • 401/402: verify the API key and separate API credit balance.

OpenCrabs Setup

Configure Fish Audio OpenAI-compatible TTS in OpenCrabs for Telegram, WhatsApp, Discord, and Slack voice replies.

PocketTavern Setup

Configure Fish Audio TTS in the PocketTavern Android app and assign a different voice to each character.

On this page

Connect Fish Audio TTS to AnythingLLMConfigure the speech providerTroubleshootingRelated documentation