stt-discord-whisper-setup

Configure whisper.cpp with Vulkan for local Hermes gateway voice transcription.

Updated Apr 19, 2026
One-click install
npx skills add https://github.com/crycriM/hermes-skills --skill stt-discord-whisper-setup
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stt-discord-whisper-setup
Source: https://github.com/crycriM/hermes-skills/tree/main/mlops/stt-discord-whisper-setup
Command: npx skills add https://github.com/crycriM/hermes-skills --skill stt-discord-whisper-setup

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcribes voice messages locally for Hermes gateway without relying on external STT services, providing fast, private transcription with no code changes required.

Core Features & Use Cases

  • Local CLI-based STT using whisper.cpp with Vulkan GPU acceleration for Hermes gateway.
  • Configurable via environment variables (VK_ICD_FILENAMES and HERMES_LOCAL_STT_COMMAND) and the Hermes config.yaml provider setting.
  • Supports Discord and Telegram voice messages; integrates with the existing transcription pipeline and voicemail handling.

Quick Start

Configure the Vulkan-enabled whisper-cli in your environment and restart the Hermes gateway to enable local STT.

Frequently Asked Questions about stt-discord-whisper-setup

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure local STT for Hermes gateway using whisper.cpp?

To configure local STT for Hermes gateway, set HERMES_LOCAL_STT_COMMAND to point to whisper-cli, configure config.yaml with the local_command provider, and restart the gateway. This enables fast, private voice transcription without external services.

Can I use Vulkan GPU acceleration for whisper.cpp voice transcription?

Yes, whisper.cpp supports Vulkan GPU acceleration for voice transcription. You must set the VK_ICD_FILENAMES environment variable to enable it, allowing the Hermes gateway to process Discord and Telegram voice messages locally with improved performance.

Does Hermes gateway support local transcription for Discord voice messages?

Hermes gateway supports local transcription for Discord voice messages via whisper.cpp CLI. By configuring the local_command provider in config.yaml and pointing HERMES_LOCAL_STT_COMMAND to whisper-cli, you achieve private, local STT processing.

What environment variables are required for whisper.cpp local STT setup?

Whisper.cpp local STT setup requires VK_ICD_FILENAMES for Vulkan GPU acceleration and HERMES_LOCAL_STT_COMMAND pointing to the whisper-cli executable. You must also configure config.yaml with the local_command provider and restart the Hermes gateway.

Why are my local voice transcriptions not working after whisper.cpp setup?

Local voice transcriptions may fail if the Hermes gateway was not restarted after config.yaml changes. Ensure VK_ICD_FILENAMES and HERMES_LOCAL_STT_COMMAND are correctly set in your environment and the local_command provider is properly configured before restarting.

Do I need external STT services if I use whisper.cpp with Hermes gateway?

No, you do not need external STT services when using whisper.cpp with Hermes gateway. It provides local, private voice transcription for platforms like Discord and Telegram by leveraging Vulkan GPU acceleration and environment-based configuration without requiring code changes.