$ loading_
An MCP tool that turns audio into raw, cleaned, or formatted text.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Gemini Transcription MCP" yet — see the docs or source repo.
Transcribe this meeting audio and output a cleaned version.
Returns a readable transcript of the meeting audio.
Output the raw transcript of this audio without extra polishing.
Returns text close to the original ASR output.
Turn this podcast audio into a formatted transcript ready for publishing.
Returns a formatted transcript suitable for publishing or editing.
Useful for developers, researchers, or office workers who need audio turned into text quickly. It can provide raw, cleaned, or formatted transcripts.
Useful for podcast, video, or interview workflows. Creators can get editable text first, then polish it for publishing or repurposing.
Useful for teams that want transcription inside their own workflow or product. The description explicitly mentions local and remote deployment.
It is an MCP server for audio-to-text transcription, using Google's Gemini API via OpenRouter. It provides raw, cleaned, or formatted transcript outputs.
The description mentions multiple outputs: raw transcripts, cleaned transcripts, and formatted transcripts.
Yes. The original description explicitly says it supports both local and remote deployment.
Transcribe audio into structured notes with speakers, timestamps, summaries, and action items.
Securely transcribe audio files or microphone recordings into usable text.
Transcribe audio, split recordings intelligently, and analyze meetings in MCP clients.
Transcribe audio and video into multiple text formats with batch processing.
Enable AI to transcribe audio, detect languages, and extract metadata.
Convert text into natural-sounding speech audio through an MCP server.