Skip to content
TranscriptDock
Sign inStart free

Site menu

TranscriptDock
Start freeSign in

Documentation

Tools
IntroductionHow it works, guides, and what you can transcribe.
QuickstartSubmit a link, wait for the job, export the transcript. Three requests.
AuthenticationAPI keys, scopes, Idempotency-Key and X-Request-Id.
JobsCreate, wait for, list, cancel and retry jobs.
TranscriptsThe transcript object and txt, srt, vtt, json exports.
BatchesUp to 50 videos in one request.
UploadsTranscribe your own audio and video files.
WebhooksGet called when a job or batch finishes; verify the signature.
ErrorsEvery error code, what it means and what to do.
Rate limitsSubmits, jobs in progress and reads per plan; the 429 response.
Pricing and credits1 credit per caption transcript, 2 per minute of AI transcription. Plans and extra credits.
SourcesYouTube, TikTok, your files and direct links: accepted URLs and modes.
MCPFind and transcribe videos from Claude, Cursor, Windsurf or your own agent.
OpenAPI SpecificationThe OpenAPI 3.1 spec for codegen and typed clients.
Claude CodeOne command adds TranscriptDock to Claude Code.
Claude DesktopAdd TranscriptDock as an MCP server in Claude Desktop's configuration file.
CursorAdd TranscriptDock as an MCP server in Cursor.
WindsurfAdd TranscriptDock to Windsurf so Cascade can find and transcribe videos.
OpenClawConnect TranscriptDock to OpenClaw autonomous agents.
19 results
Reference

Sources

YouTube, TikTok, your files and direct links: accepted URLs, what each mode does, and limits.

Whatever the source, you get the same transcript object: text, timed segments, and word timings when AI transcription produced it. Limits for every source: 2 hours and 250 MB.

Sources#

SourceAccepted linkscaptions_onlyauto / transcribe
YouTubeyoutube.com/watch?v=…, youtu.be/…, /shorts/…, /live/…Creator or automatic captions, 1 creditPaid plans
TikToktiktok.com/@user/video/…, vm.tiktok.com/… share linksCreator captions, 1 creditPaid plans
Your filemp3, wav, m4a, ogg, aac, mp4, webm via POST /v1/uploadsNot availablePaid plans
Direct linkAny public https URL that serves an audio or video fileNot availablePaid plans

GET /v1/capabilities with your key returns this table for your plan, so a client can show only what will work.

Captions#

  • Public videos only. Private, members-only and age-gated videos fail with a SOURCE_* code.
  • YouTube has two kinds: captions the creator uploaded and YouTube's automatic ones. caption_preference picks; the default takes the creator's when present.
  • caption_languages asks for specific tracks, e.g. ["es", "en"]. POST /v1/language-discoveries lists what a YouTube video has.
  • Timing is per caption cue (timing_granularity: "segment").

AI transcription#

  • Listens to the audio; works with or without captions. Detects the language, or takes a hint in language.
  • Returns word timings and confidence (timing_granularity: "word").
  • Takes roughly a quarter of the media length. Use ?wait=25 or a webhook rather than tight polling.
  • 2 credits per started minute, 1 minute minimum; cap a job with max_credits.