$ loading_
Transcribe audio into text via local processing or OpenAI Whisper API for fast conversion.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Whisper Transcribe" MCP server from askskill: Run: claude mcp add 'io-github-zahirinatzuke-whisper-transcribe-mcp' -- uvx whisper-transcribe-mcp
Office staff or researchers often need to revisit meeting audio. They can first transcribe it into text and then quickly search key points and decisions.
Content creators can transcribe course and interview audio into text, then quickly generate outlines, summaries, or rewritten materials.
When sensitive data should stay local, users can choose faster-whisper mode so the transcription is handled without leaving the local environment.
Whisper Transcribe is an MCP tool for transcribing audio to text. It supports local transcription with faster-whisper and transcription through the OpenAI Whisper API.
Local mode runs with faster-whisper on your local environment, while API mode uses OpenAI Whisper. For detailed performance and parameter differences, see the source repository.
The available description does not include full setup steps. If you use API mode, you usually need the required runtime and credential configuration; check the source repository for exact details.
Transcribe audio to text locally with Whisper CLI, no API key required.
Transcribe audio into text or speaker-separated transcripts with OpenAI APIs.
Transcribe audio or video to text with optional speaker labeling.
Transcribe local audio files with Whisper and optionally include timestamps.
Transcribe audio into text with Whisper models over stdio or HTTP.
Transcribe audio and video into multiple text formats with batch processing.