Video Transcription API & MCP Server
Turn video to text from code or from any AI agent. One REST API with an MCP server, CLI, and agent Skill on top — 99% accuracy, 100+ languages, speaker labels, and SRT/VTT subtitle export.
REST API
Transcribe video to text with one API call
POST a video URL and get back a structured JSON transcript with speaker labels and word-level timestamps. Webhooks notify you the moment it's ready — no polling.
- 100+ languages
- Speaker diarization
- SRT · VTT · TXT · PDF
- HMAC-signed webhooks
curl https://www.transcribevideototext.com/api/v1/transcriptions \
-H "Authorization: Bearer vtt_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"url": "https://example.com/interview.mp4",
"language": "auto",
"diarize": true
}'AI agents
Give Claude.ai the power to hear
Connect to Claude Code, Cursor, Codex, and Claude Desktop — or any agent — and transcribe video to text right from your chat. 100+ languages, speaker labels, and webhooks included.
- Built for AI agents
- MCP, CLI, or REST API
- Webhooks, not waiting
- Production-ready
- 1
Open Connectors
In Claude.ai: Settings → Connectors → Add custom connector.
- 2
Paste the MCP URL
Enter the URL, then Connect and sign in. OAuth — no API key to paste.
https://mcp.transcribevideototext.com/mcp - 3
Transcribe from chat
Ask Claude.ai to transcribe a video URL — speakers labeled, 100+ languages.
FAQ