# Hermes Agent + Whisper

Hermes Agent + Whisper is an Unraid community template that bundles the official Nous Research Hermes Agent with faster-whisper for local, GPU-accelerated speech-to-text. It is open source and self-hosted, installable on Unraid.

Canonical page: https://ourlocalhost.com/app/2884/hermes-agent-whisper

## Description

Hermes Agent + Whisper is an Unraid community template that bundles the official Nous Research Hermes Agent with faster-whisper for local, GPU-accelerated speech-to-text. It lets homelabbers run the self-hosted AI agent on their own hardware with on-device voice transcription built in, so you can use the agent and transcribe audio without sending data to the cloud.

## Platform availability

Available on 1 of 10 platforms: Unraid.

## Health score

62/100 (Good), based on 4 of 4 factors.
- Maintained: 70 (last commit 23 days ago)
- Popular: 100 (258,451 GitHub stars)
- Easy to install: 35 (1 install platform, install notes, Docker image)
- Light to run: 10 (8 GB minimum RAM)

## Links

- Official website: https://hermes-agent.nousresearch.com/
- Unraid: https://ca.unraid.net/apps/hermes-agent-whisper-0nedlwm1k26i8a?q=Hermes-Agent-%2B-Whisper
- GitHub: https://github.com/nousresearch/hermes-agent
- Documentation: https://hermes-agent.nousresearch.com/docs/user-guide/docker

## Common questions

### Do I need to install CUDA on the Unraid host for GPU-accelerated transcription?

No. GPU acceleration works out of the box with the NVIDIA Unraid plugin, and faster-whisper plus its CUDA runtime wheels are bundled in the image.

### Which ports should I expose for the Hermes Agent + Whisper dashboard and API?

Expose port 9119 for the Dashboard WebUI and port 8642 for the API.

### How do I change the Whisper model size used for transcription?

Set the WHISPER_MODEL variable to choose the desired faster-whisper model size, such as tiny, base, small, or medium.

### Where are the agent’s configuration, sessions, and API keys stored, and how does that affect upgrades?

The container stores config, API keys, sessions, skills, and memories in a single host-mounted directory, /opt/data. The image itself is stateless, so you can pull a new version without losing configuration.

### How can I verify that Hermes Agent is installed and able to use a model?

Run hermes doctor and then a quick hermes chat -q "Hello" test to confirm the agent is available and can talk to your model. If this fails, the agent cannot start useful work yet.

### Can I switch between model providers without changing code?

Yes. You can use Nous Portal, OpenRouter, OpenAI, your own endpoint, or other supported providers. Use the hermes model command to switch without code changes.

## Alternatives

- Goose OSS: An Open Source AI Agent (think Claude CoWork) that help you to automates engineering tasks seamlessly with local execution, customization,…
- Hermes Agent: Hermes Agent is a self-improving AI agent by Nous Research that creates and refines skills from experience, builds a persistent model of yo…
- Khoj: Khoj is an open-source AI personal assistant and second brain.
- Kimi: AI tool for reasoning across math, coding, and image analysis, processing up to 128k tokens, handling visual data, benchmarks, and chain-of…
- LocalAI: LocalAI is a free, open-source, self-hosted AI engine that provides a drop-in, OpenAI-compatible API for running local models.
- Maid (AI): Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.
- Manus: Transforms thoughts into actions with personalized travel itineraries, stock analysis, and educational content while autonomously completin…
- Odysseus: Self-hosted AI workspace with chat, agents, deep research, documents, email, calendar, and model Cookbook.
- OpenClaw: OpenClaw is an open-source, self-hosted AI assistant gateway that connects large language models (LLMs) to Discord, Telegram, and WhatsApp,…
- Poe: Poe is a web-based AI platform that hosts multiple assistant bots—including Claude and various GPT and image/audio models—to provide conver…
- Together Chat: Together Chat is a next-generation consumer app designed to let you interact seamlessly with today's most popular open-source models, inclu…
- nanoclaw: NanoClaw is a lightweight, secure personal AI assistant that runs each agent in its own isolated container on your own server.

---
Source: Our Local Host (https://ourlocalhost.com/app/2884/hermes-agent-whisper), the self-hosted and open-source app directory.
