Hermes OmniVoice TTS Plugin: plugin for Hermes Agent

Community plugin that adds the local OmniVoice text-to-speech model as a Hermes Agent TTS provider

What Hermes OmniVoice TTS Plugin does

Once enabled, the plugin registers a TTS provider named omnivoice, so the existing Hermes text_to_speech flow can synthesize speech through OmniVoice without changes to Hermes core. OmniVoice is a local, multilingual, zero-shot model, and the README says it supports more than 600 languages.

Three voice modes are available. Auto lets the model pick a voice, voice design takes a description such as "female, low pitch, british accent", and voice cloning uses a short reference audio file with an accurate transcript. Voice values can also be passed at call time with instruct: or ref: prefixes, or as the path of an existing audio file. Settings live under tts.omnivoice in ~/.hermes/config.yaml, including model, device and dtype, and the README mentions controls for speed, diffusion steps, guidance scale and duration. A lighter install without the OmniVoice runtime is also offered.

Key features

Registers an omnivoice TTS provider for Hermes without modifying Hermes core
Multilingual speech in the 600+ languages OmniVoice supports
Voice design from a text description of gender, pitch, age or accent
Voice cloning from a short reference audio clip
Local inference with configurable model, device and dtype

When to use it

Giving a Hermes agent a custom or cloned voice
Producing voiceovers for product demos and tutorials
Generating multilingual narration locally instead of through a hosted TTS service

Who it is for: Hermes Agent users who want local, customizable text-to-speech with voice cloning or voice design.

How it fits with Hermes Agent

A community plugin for Hermes Agent that adds a TTS provider, enabled with hermes plugins enable omnivoice.

How to install Hermes OmniVoice TTS Plugin

These commands are copied from the project's README. Check the repository for the latest steps before you run them.

pip install "hermes-omnivoice[omnivoice] @ git+https://github.com/ThaungThanHan/hermes-omnivoice.git"
hermes plugins enable omnivoice
hermes config set tts.provider omnivoice

Requirements: The OmniVoice runtime installed in the same Python environment that runs Hermes

FAQ

What is Hermes OmniVoice TTS Plugin?

Hermes OmniVoice TTS Plugin is a community plugin that connects the local OmniVoice text-to-speech model to Hermes Agent. It adds an omnivoice provider for multilingual speech, voice design and voice cloning.

How do I install Hermes OmniVoice TTS Plugin?

Install the package with pip in the Python environment that runs Hermes, then run hermes plugins enable omnivoice and hermes config set tts.provider omnivoice. Restart Hermes after changing the config.

Is Hermes OmniVoice TTS Plugin free and open source?

The repository has no license file, so default copyright applies and you should check with the author before reuse. OmniVoice itself is a separate project from k2-fsa.