Voice Assistant Workflows
Set up voice input and output for the Hermes agent so you can talk to it through a terminal microphone loop, Telegram or Discord voice notes, or a Discord voice channel and get spoken replies — all with the same agent, memory, and skills.
Requirements
- Choose a TTS provider: xAI TTS is auto-wired when using an xAI endpoint, ElevenLabs and other TTS backends are configured in
config.yaml. For transcription, Whisper (local or API) is the typical pick. - The Voice & TTS toolset enabled (
hermes tools). - A TTS provider (xAI TTS, ElevenLabs, or compatible).
- Transcription (Whisper local or API).
- A messaging gateway for the platform you're using (Telegram, Discord).
How to use
Voice is mostly transparent to prompting — you speak the same way you'd type. Useful patterns:
Short spoken tasks that would be annoying to type: “add milk and coffee to the grocery list”
Hands-free status checks: “what's on my calendar tomorrow?”
Driving/walking: “send a Telegram to my partner saying I'll be 20 minutes late”
Latency is dominated by transcription and TTS, not the model turn. For responsiveness, a fast local Whisper and a streaming TTS provider make the biggest difference.
Voice-channel mode in Discord is the most finicky — it needs persistent voice permissions on the bot and a VPS with outbound UDP unimpeded.
Termux on Android has voice limitations noted in the official repo — the .[termux] extra deliberately skips some voice deps.
Setup
Voice is enabled through hermes tools and provider config. The fast path:
hermes setup # the wizard offers voice configuration
hermes tools # enable the Voice & TTS toolset explicitly
Specific messaging platforms need their gateway enabled (Telegram, Discord). The Discord voice-channel bot mode has its own docs section — join the channel manually or have the agent join on a trigger word.
Source: aliaihub/awesome-hermes-usecases and its contributors. License: CC-BY-4.0. Source license notice.
Translation and editorial adaptation by ClawCases.
>Resources
>Related Use Cases
1-3-1 Communication Rule Decision Brief
Writes 1-3-1 decision briefs for tasks with multiple viable approaches, producing a one-sentence problem framing, three options with pros and cons, and a single recommendation with definition of done and implementation plan.
AI-Powered Earnings Tracker
Stay on top of earnings season across dozens of tech companies without manually checking multiple sources and remembering report dates for every AI/tech earnings report.
Dynamic Dashboard with Sub-agent Spawning
Set up a live dashboard that spawns sub-agents to fetch metrics in parallel from multiple data sources, aggregates the results, and delivers formatted updates automatically.