local-voskLocal speech-to-text using Vosk. Lightweight, fast, fully offline. Perfect for transcribing Telegram voice messages, audio files, or any speech-to-text task without cloud APIs.
Install via ClawdBot CLI:
clawdbot install sfkiwi/local-voskLightweight local speech-to-text using Vosk. Fully offline after model download.
# Transcribe Telegram voice message
./skills/local-vosk/scripts/transcribe voice_message.ogg
# Transcribe any audio
./skills/local-vosk/scripts/transcribe audio.mp3
# With language (default: en-us)
./skills/local-vosk/scripts/transcribe audio.wav --lang en-us
Any format ffmpeg can decode: ogg (Telegram), mp3, wav, m4a, webm, flac, etc.
Default model: vosk-model-small-en-us-0.15 (~40MB)
Other models available at https://alphacephei.com/vosk/models
pip3 install vosk --user --break-system-packages
# Download model
mkdir -p ~/vosk-models && cd ~/vosk-models
wget https://alphacephei.com/vosk/models/vosk-model-small-en-us-0.15.zip
unzip vosk-model-small-en-us-0.15.zip
Generated Mar 1, 2026
Automatically transcribe Telegram voice messages (.ogg format) into text for users who prefer reading over listening. This is particularly useful in noisy environments or for users with hearing impairments, providing instant text conversion without cloud dependency.
Transcribe business meetings or interviews recorded as audio files in various formats (mp3, wav, m4a) without requiring internet connectivity. Ideal for confidential discussions where cloud-based services pose security risks or in areas with poor internet access.
Convert lecture recordings or educational audio materials into text for students who benefit from written content. Enables offline study materials creation and supports learners with different preferences without recurring API costs.
Transcribe interviews or field recordings made by journalists in remote locations with limited internet. Provides quick text drafts for article preparation while maintaining source confidentiality through local processing.
Convert personal voice memos and recordings into searchable text archives. Helps users organize thoughts, reminders, or creative ideas captured verbally without relying on cloud storage or subscription services.
Sell the skill package as a standalone offline transcription tool with lifetime usage rights. Customers pay once for perpetual access to local STT capabilities without recurring fees, appealing to privacy-conscious users and organizations.
Offer custom integration services to businesses wanting to embed offline speech-to-text into their existing applications (e.g., customer service platforms, internal tools). Charge for implementation, customization, and technical support.
Package the skill with optimized hardware (single-board computers, dedicated devices) for specific use cases like offline transcription kiosks or secure recording devices. Target industries requiring turnkey offline solutions.
💬 Integration Tip
Ensure ffmpeg is installed on the target system for format compatibility, and guide users to download appropriate Vosk models for their language needs from the official repository.
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Full desktop computer use for headless Linux servers. Xvfb + XFCE virtual desktop with xdotool automation. 17 actions (click, type, scroll, screenshot, drag,...
Essential Docker commands and workflows for container management, image operations, and debugging.
Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge
Deploy applications and manage projects with complete CLI reference. Commands for deployments, projects, domains, environment variables, and live documentation access.
Monitor topics of interest and proactively alert when important developments occur. Use when user wants automated monitoring of specific subjects (e.g., product releases, price changes, news topics, technology updates). Supports scheduled web searches, AI-powered importance scoring, smart alerts vs weekly digests, and memory-aware contextual summaries.