- Home
- Skills
- Workflow Automation
- Local Speech-to-Text with Whisper
Local Speech-to-Text with Whisper
Generate optimized OpenAI Whisper CLI commands for local, private audio transcription and translation.
$5
Works with the AI Agents you already use
Local Speech-to-Text with Whisper
Example session with this skill installed
I need to transcribe conference_call.mp3. I want a high accuracy transcript in srt format saved to the current directory.
- Read your context and instructions
- Compiled the local speech-to-text
I have generated the command for a high-accuracy transcription of your audio file using the medium model to balance precision and performance.
Transcription Command
# Ensure you have whisper installed: pip install openai-whisper
# This command uses the medium model for high accuracy and outputs srt.
whisper conference_call.mp3 \
--model medium \
--output_format srt \
--output_dir . \
--verbose False
Configuration Details
| Parameter | Value | Description |
|---|---|---|
| Model | medium | High accuracy, requires ~5GB VRAM. |
| Format | srt | SubRip Subtitle file with timestamps. |
| Task | transcribe | Standard speech-to-text. |
| Output Dir | . | Current working directory. |
Next steps
- Run the command in your terminal where the audio file is located.
- If the first run is slow, check
~/.cache/whisperto ensure the model has finished downloading. - If you experience memory issues, swap
--model mediumfor--model small.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Transcribing audio files usually involves expensive API costs or sending sensitive data to third-party servers. Managing local Whisper CLI flags for different file formats and translation tasks is tedious and error-prone.
What it does
- Generates precise Whisper CLI commands for local audio transcription.
- Handles language translation tasks from audio to English text.
- Configures model selection based on your hardware constraints and accuracy requirements.
- Specifies output formats including SRT, TXT, and VTT for various workflows.
Frameworks & tools
OpenAI Whisper CLI, FFmpeg, and Python.
Why this beats prompting it yourself
This skill eliminates the need to memorize complex CLI flags or look up model names. It ensures you use the correct syntax for local paths and task types, preventing failed runs on large audio files.
Use cases
- Convert podcast recordings or meetings into text transcripts locally.
- Generate SRT subtitle files for video production workflows.
- Translate non-English audio files directly into English text.
- Batch process audio files using optimized model selection.
Known limitations
Requires Whisper CLI and FFmpeg installed on the local system. Large models require significant RAM and GPU resources.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.
Requires Whisper CLI and FFmpeg installed locally. Performance depends on hardware; larger models (large/medium) require significant VRAM or RAM.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Permissions
No special permissions declared or detected