Audio API
From its catalog listing
OpenAI-compatible /v1/audio/transcriptions and /v1/audio/speech endpoints backed by Hermes' configured STT and TTS providers.
Good to know before installing
opens an HTTP listener (127.0.0.1:8643 by default) that starts with the gateway as soon as a key exists, protected by a bearer key (AUDIO_API_KEY, or the API server's API_SERVER_KEY when reuse is on, which is the default); uploaded audio and requested text go to whichever STT/TTS providers Hermes is configured to use; runs ffmpeg when it must convert the output format; calls Hermes' internal transcription and TTS helpers, which are not a stable plugin API.
From its catalog listing.
How to install
- Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.
hermes plugins install hermes-audio-api - Said no? Turn it on later:
hermes plugins enable hermes-audio-api - Restart Hermes so it loads the plugin.
Some plugins also need a sign-in or settings: see Full setup & settings. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide (opens in a new tab).
- Category
- Chat apps & voice
- Maintained by
- axAilotl (Community)
- Needs
- No API keys declared
- Works on
- linux, macos, windows
- Needs Hermes
- 0.23.0 or newer
- Version
- 0.1.0
- In the catalog
- 2026-11-10
Known issues (from its catalog listing)
- Calls Hermes' transcription and text-to-speech helpers, which are outside the documented plugin API; tested against 0.23.0 and main.
- Listens on its own port because plugins cannot add routes to the built-in API server.
Using the Hermes desktop app? See where plugins live

Full setup & settings ↗Source code ↗
More in chat apps & voice
New Hermes Agent updates every day on X. Follow @HermesWatcher