IdealPhase Audio Tags

From its catalog listing
Hermes plugin that adds a few honest ElevenLabs delivery tags so speech sounds more human. It does not replace the built-in ElevenLabs voice provider, and it does not change the chat transcript.
Good to know before installing
sends the prepared speech, voice ID, model ID, and any pronunciation-dictionary locator to api.elevenlabs.io with your ELEVENLABS_API_KEY; synthesis is billed to your ElevenLabs account. When automatic tags are on, the untagged transcript is also sent to the model configured for auxiliary.idealphase_elevenlabs_audio_tags, or your normal chat model if you did not pin one. Audio is written only to the path Hermes requests. No tools, hooks, or middleware. Does not store the key, phone home, or log the transcript.
From its catalog listing.
How to install
- Install it. Hermes asks for any API keys it needs (this one needs
ELEVENLABS_API_KEY), then asks whether to turn it on.hermes plugins install idealphase-elevenlabs-audio-tags - Said no? Turn it on later:
hermes plugins enable idealphase-elevenlabs-audio-tags - 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
- IdealPhaseLLC (Community)
- Needs
ELEVENLABS_API_KEYAPI key- Needs Hermes
- 0.21.5 or newer
- Version
- 0.1.1
- In the catalog
- 2026-11-02
Known issues (from its catalog listing)
- If the tag model misses the no-progress window, speech still goes out, without tags.
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