Introduction

The VideoToText API lets you submit audio or video and retrieve transcripts from your own apps, scripts, agents, or automation tools (n8n, MCP, and more).

Transcription is asynchronous: you create a job, then either poll its status or receive a webhook when it finishes. Large files never flow through your code — you either upload directly to storage or hand us a public URL to fetch.

Base URL

https://www.transcribevideototext.com/api/v1

The machine-readable spec is served by the API at /api/v1/openapi.json — import it into Postman, Insomnia, or a client generator.

Quickstart

curl -X POST https://www.transcribevideototext.com/api/v1/transcriptions \
  -H "Authorization: Bearer vtt_your_key" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com/audio.mp3","language":"auto"}'
# → { "id": "…", "status": "pending" }

curl https://www.transcribevideototext.com/api/v1/transcriptions/{id} \
  -H "Authorization: Bearer vtt_your_key"
# → { "status": "completed", "segments": [ … ], … }

What's next

• Authentication — API keys and the Authorization header.
• Create a transcription — upload vs. URL ingest, options.
• Retrieve results — status, segments, and listing.
• Webhooks — get pushed events instead of polling.
• Rate limits and Errors.