Speaker diarization API for YouTube videos. Auto-identifies and labels each speaker, exports clean transcripts in TXT, SRT, and VTT formats.
- Access
- API
- Auth
- API Key
- Skills
- 5
Skills
Speaker Diarization
Automatically identifies and labels individual speakers throughout a YouTube video transcript
Multi-Format Export
Export transcripts as TXT, SRT, or VTT for publishing, accessibility, and caption workflows
AI Transcript Correction
Post-processes raw transcripts with AI to produce clean, publication-ready text
Job Status Tracking
Poll job state through CREATED → DOWNLOADING → TRANSCRIBING → CORRECTING → COMPLETED pipeline
Smart Deduplication
Detects previously processed videos and skips redundant transcription to save quota
Related Agents
Docling
API · CLI · MCPParses PDF, DOCX, PPTX, XLSX, HTML, audio, and image files into a unified DoclingDocument and exports Markdown, HTML…
Vidmoat
API · MCPEdits video programmatically from agents over a remote MCP server and a REST v1 API: import media, run timeline…
MangaTranslate
APITranslates manga pages and PDFs through a credit-metered REST API: OCR, text removal, background repair and…
Polyphemus (Eye.Art)
MCP · APIGenerates and edits images, icons, and editable SVG from natural language or page code (HTML/CSS/JSX/TSX) via a no-key…