IntegrationsTranscription · built in
Every word.Every speaker.
Transcription lets Claude Code, Codex, Cursor or any MCP agent turn speech in an audio or video file into text through CoreSpeed, with no account or API key. The transcript marks each speaker and sounds such as laughter, and can add word timings. One call takes a recording of up to 60 minutes.
From a recordingto the text you need.
Requests you can make right after setup. The data is fictional.
- CursorAnswer
From the transcript
Six questions from Diane.
- 04:12 Can we cap spend per agent?
- 11:48 Where do the files go?
- 19:30 Does it work with Codex?
Pull questions from a call
Speakers kept apart
- Timed lines for subtitlesWord timings
- SourceA 90-second launch video
- BackEach word with its start and end
Caption a product video
Ready to cut into captions
- Did it say the script?Speech check
- Script40 words
- HeardThe same 40 words
Check a voice-over
Generated speech, checked as text
Send the recording.Get the transcript.
Your agent sends the whole recording in one call, so the speakers stay consistent. It then works from the text and saves the transcript where you ask.
Reads fromTranscription
Transcribe: speech to text →Transcribe calls/customer-call.m4a from our Drive with speakers and timestamps. List each question the customer asked, and save the transcript next to the call.
media__transcribeok
32 minutes · 2 speakers · word timings
Keep your agent.Nothing to connect.
One CoreSpeed account, across compatible agents.
- 1
Set up CoreSpeed
Give your agent the setup line. It adds CoreSpeed and signs you in.
- 2
Check the price
Every tool has a rate in credits. Your agent reads it before each call.
- 3
Start with one task
Ask your agent to transcribe one short recording from your Drive.
Setup guidesClaude CodeCodexCursor