openai-whisper

by Unknown v1.0.0

Local speech-to-text with the Whisper CLI (no API key).

openai whisper

What It Does

Transcribes audio files to text locally using the OpenAI Whisper CLI tool. Supports various audio formats, models, and output formats.

When To Use

When you need to transcribe audio files locally without an API key, translate audio, or generate subtitles. Ideal for privacy-sensitive data or offline use.

Inputs

Audio file path, Whisper model size (e.g., tiny, base, small, medium, large), output format (e.g., txt, srt, vtt), and output directory.

Outputs

Text transcription of the audio file in the specified format and directory.

Limitations

Transcription accuracy depends on the selected Whisper model size and audio quality. Larger models provide better accuracy but require more computational resources. Initial model download can take time depending on network speed.

Installation

1. Ensure you have Homebrew installed: `/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"`
2. Install OpenAI Whisper using Homebrew: `brew install openai-whisper`.
3. Verify the installation by running `whisper --help` in your terminal.

View Cline documentation 

1. Open Cursor IDE.
2. Add the skill by referencing the repository URL: https://github.com/openclaw/openclaw/tree/main/skills/openai-whisper in your Cursor project.
3. Install the required dependencies by running `brew install openai-whisper` in your terminal.

View Cursor IDE documentation

Related Skills You May Like

Discover more AI agent skills in the same category to enhance your workflow automation.

Explore All Skills

Have a Skill to Share?

Join the community and help AI agents learn new capabilities. Submit your skill and reach thousands of developers.

Submit Your Skill Learn How