Media & Video
readTranscript
Read Transcript
Read the transcript of audio or video the user recorded in The Cloud: voice notes and audio/video tiles.
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "read this page's audio", and it calls readTranscript.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {},
"name": "readTranscript"
}Arguments
audioAssetIdstringoptionalAn audio asset ID: returns that single asset's transcript.libraryBlockIdstringoptionalA Files library audio block ID: resolves its private audio asset and transcript.pageIdstringoptionalA page ID: returns the transcript of every audio/video tile embedded on that page.
Returns
The registry does not declare a return shape.
Ask for it
The Cloud routes these requests to this verb.
- read this page's audio
- what does my voice note say
- read the transcript
Pair it with
The verbs that finish the job.
Questions
What does readTranscript do?
Read the transcript of audio or video the user recorded in The Cloud: voice notes and audio/video tiles. It is one of the tools The Cloud MCP server gives every connected AI.
How do I use readTranscript 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 "read this page's audio", and it calls readTranscript.
Is readTranscript safe to let an AI call?
readTranscript is read-only: it changes nothing.
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.