- TEXT
- STATUS
- ERRORS
- HUMAN
Short answer
How can I transcribe many audio files at once with my AI?
You use the stt_batch tool to send multiple files to Cartesia for simultaneous transcription. This turns your audio files into text without you needing to process them one by one. You'll get a full set of transcriptions once the job finishes.
The results of your batch job.
Where your transcriptions land.
The AI handles the heavy lifting of the conversion process.
TEXT
Written transcripts
The tool converts your audio into text. You'll receive the written content for every file in your batch.
STATUS
Job progress tracking
Your AI monitors the batch. You can see which files are currently being processed and which are finished.
ERRORS
Failed file reports
If a file is unreadable, the AI flags it. You'll know exactly which specific files need attention.
HUMAN
Manual review required
The AI provides the text, but you'll need to read through it to check for accuracy or context.
The workflow
What your AI does when the audio arrives.
The AI manages the queue so you don't have to manually trigger every single file.
Batch preparation
Your AI gathers the audio files you've identified and prepares them for the batch request.
stt_batchAudio conversion
The tool sends the audio data to Cartesia to be turned into text.
stt_batchProgress monitoring
The AI tracks the status of the batch to ensure every file is being handled.
stt_batchText delivery
Once the transcription is done, the AI presents the text directly in your chat.
stt_batch
Try it
Copy these to start.
Use these prompts to kick off your transcription jobs.
Starting points
Replace the folder or file names with your actual data.
Cartesia Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_fqUkC4o6TEWq9kAU8DlY8MAb7pfJxo3R952S85p7/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Cartesia capabilities are ready to use.
{
"mcpServers": {
"cartesia-voice-ai-mcp": {
"url": "https://edge.vinkius.com/vk_preview_fqUkC4o6TEWq9kAU8DlY8MAb7pfJxo3R952S85p7/mcp"
}
}
}Transcribe all the audio files in my 'interviews' folder.
Run a batch transcription for the files listed in this spreadsheet.
Use stt_batch to transcribe the recordings from the 'client_calls' directory.
Transcribe these three specific MP3 files for me.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Cartesia once, then ask.
Connect your account once and your AI client will have immediate access to the transcription tools. You can find the full setup guide on the Connector page.
Connect Cartesia to your AIFAQ
How the transcription task behaves.
- 01
Can the AI edit my original audio files?
No. The tool only reads the audio to generate text. It cannot change or delete your original files.
- 02
Does the AI save the transcripts to my computer?
No. The AI provides the text in your chat window. You'll need to copy and save it yourself.
- 03
What happens if one file in the batch is broken?
The AI will report that specific file as a failure, but it will continue processing the rest of the batch.
- 04
Can I transcribe video files?
No. The tool is for audio files. You'll need to extract the audio from a video before sending it to the AI.
- 05
How many files can I send at once?
The batch tool is designed to handle large groups of files in a single request.
More questions about Cartesia? The Connector page answers them. See everything the Cartesia Connector can do
Connect Cartesia to Claude, Cursor, ChatGPT & more
