Media & Video
transcribeMedia
Transcribe Media
Transcribe spoken video or audio into a private, timestamped transcript (word timings + speaker diarization), reusing the shipped Deepgram/Whisper ASR.
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "transcribe this video", and it calls transcribeMedia.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {},
"name": "transcribeMedia"
}Arguments
audioAssetIdstringoptionalA My Music track or a recording: the audioAssetId (or the audioAsset:<id> trackId) that importAudioToLibrary or a recording returned. Provide exactly one source.confirmbooleanoptionalRequired when the source is the member's own private content: a devicePath, or a url that is a YouTube upload of theirs that is not public. Set it to true ONLY when the member asked for this source in words in this conversation. Never set…devicePathstringoptionalFull path to a media file on the member's own attached machine, starting at /. Nothing is uploaded and there is no size limit. Provide exactly one source.fileRefobjectoptionalA media-pool or uploaded asset to transcribe. Provide this OR pageMediaBlockId, not both.libraryBlockIdstringoptionalA Files library audio block to transcribe. Provide exactly one source.machineIdstringoptionalWhich attached machine holds the devicePath. Omit to use the member's healthy online machine.pageMediaBlockIdstringoptionalAn on-page audio/video media block to transcribe. Provide this OR fileRef, not both.urlstringoptionalA video or audio URL to transcribe. A link that serves an audio file (up to 100 MB) is fetched and transcribed in The Cloud; any other link is resolved on the member's machine. Provide exactly one source.
Returns
A devicePath, or any other url (a YouTube page, an article, a video), is resolved on the member's machine, which extracts the audio track and carries out that alone: nothing of a local file is ever…
Ask for it
The Cloud routes these requests to this verb.
- transcribe this video
- video to text
- get the transcript of this clip
- caption this audio
Pair it with
The verbs that finish the job.
Questions
What does transcribeMedia do?
Transcribe spoken video or audio into a private, timestamped transcript (word timings + speaker diarization), reusing the shipped Deepgram/Whisper ASR. It is one of the tools The Cloud MCP server gives every connected AI.
How do I use transcribeMedia from Claude or ChatGPT?
Connect your AI to The Cloud at https://mcp.thecloud.so/mcp and sign in once. Then ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "transcribe this video", and it calls transcribeMedia.
Is transcribeMedia safe to let an AI call?
transcribeMedia widens who can see or receive something, so the owner approves every call explicitly. An AI cannot approve it for itself. It reaches a system outside The Cloud on your behalf.
Connect
One endpoint gives your AI this tool and every other one: connect Claude, ChatGPT, Cursor or Gemini, read what The Cloud is, or see pricing.