POST audio or video
Upload a file or provide a remote HTTPS source with your retention preference.
MJ Audio Intelligence · Commercial API
Media in. Structured intelligence out.
A private, asynchronous processing service for companies that need transcripts, speaker labels, timestamps, subtitles, and machine-readable results from audio or video.
2¢ / minuteApproved launch price
Job-based APIPoll or receive a webhook
Retention controlsDelete sources automatically
Built for integration
One request starts the complete workflow.
Submit a secure file upload or public media URL. The service immediately returns a job ID, processes the media asynchronously, and delivers a structured result through polling or a signed completion webhook.
Open the developer portalReceive a job ID
Track queued, processing, completed, or failed status without holding a connection open.
Poll or use a webhook
Retrieve JSON, SRT, and VTT results when processing completes.
Useful output, not just plain text.
- Transcripts and word timestamps
- Speaker diarization
- SRT and VTT subtitles
- Structured JSON
Designed for company systems.
- API-key authentication
- Asynchronous job queue
- Signed completion webhooks
- OpenAPI documentation
Keep source media short-lived.
- Automatic source deletion
- Customer-selected retention
- Customer-scoped results
- Square usage invoicing
Launch pricing$0.02per processed minute
Start with the 1,200-minute pilot for $24, then move to consolidated Square usage invoices.
View pricing and pilotAPI questions
Audio Intelligence integration questions
Answers for teams evaluating transcription, diarization, subtitle generation, media retention, and usage pricing.
What does the Audio Intelligence API return?
Completed jobs can return transcripts, word timestamps, speaker diarization, structured JSON, SRT subtitles, and VTT captions for audio or video inputs.
How does asynchronous media processing work?
Submit a secure file upload or remote HTTPS source and receive a job ID immediately. Your application can poll job status or receive a signed webhook when processing completes.
How is source-media retention controlled?
The service supports automatic source deletion and customer-selected retention settings so uploaded media can remain short-lived while completed results stay scoped to the customer.
What does the transcription API cost?
Launch pricing is $0.02 per processed minute. A 1,200-minute pilot costs $24, with consolidated Square usage invoices available after the pilot.
Developer-ready
Connect your first workflow.
The developer portal includes API documentation, job submission, key management, usage history, retention settings, and service health.
Open MJ Audio Intelligence