Provide an accessible audio or video file and choose the transcript, speakers, and subtitles you need.
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
Process a recording with speaker identification and retrieve its transcript after completion.
/oo Gladia: Start a Gladia transcription for [public audio URL] with speaker identification and [language preference]. Check the job until complete and summarize the transcript with speaker references.
Request subtitles in the desired format when processing a recording.
/oo Gladia: Transcribe [public media URL] with Gladia and generate subtitles in [subtitle format]. Retrieve the completed job and show its subtitle result.
Set up oo CLI and the oo Skill in your agent.
Install OOMOL →Connect your Gladia API key.
Connect Gladia →Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →Choose Your Agent
Gladia processes pre-recorded media asynchronously and provides job records, transcript results, and optional language or analysis features.
Start transcription with optional speaker, subtitle, translation, and analysis settings, then read the result.
Upload transit media, list jobs, download original audio, or delete a job and its data.
Upload an audio or video file up to 100 MiB from connector transit storage to Gladia.
Leina 
Wanta 
gladia.upload_file Start an asynchronous Gladia pre-recorded transcription job from a public audio or video URL.
gladia.start_transcription Retrieve a Gladia pre-recorded transcription job by ID, including results when done.
gladia.get_transcription List Gladia pre-recorded transcription jobs with optional pagination, date, status, and metadata filters.
gladia.list_transcriptions Download the original audio file for a Gladia pre-recorded transcription and store it in connector transit storage.
gladia.download_transcription_audio Delete a Gladia pre-recorded transcription job and its associated data.
gladia.delete_transcription No matching tools.
No. Submission starts a job and provides its ID. Retrieve that job later to check its status and access completed results.
Yes. Ask to enable speaker identification when starting transcription. You can also specify relevant speaker settings for the recording.
Place it in connector transit storage and upload it to Gladia, then use the resulting media URL for transcription. A public audio or video URL can be used directly.
Manage which optional storage OOMOL can use. You can change these choices from the footer at any time.