Agent Body modelsapi generation api

agentbody/tiktok-transcribe

Transcribe TikTok video audio into text and timed segments. Use when existing captions are unavailable and explicit audio transcription is needed. Limited to 10-minute videos.

Input
Idle

Example output — click Run to generate your own

API README

TikTok Transcribe

Transcribe TikTok video audio into text and timed segments using speech recognition.

Highlights

  • Full audio-to-text transcription for TikTok videos
  • Returns timed segments with precise timestamps
  • Automatic language detection
  • Limited to videos up to 10 minutes

Pricing

ComponentPrice
Per transcription$0.01

When to Use

✅ Good fit❌ Consider alternatives
Videos without existing captionsVideos with available subtitles (use tiktok-transcript)
Audio content analysisVideos longer than 10 minutes
Accessibility needsNon-TikTok platforms

Technical Specs

SpecValue
MethodPOST
Endpoint/v1/tiktok/transcribe
InputTikTok video URL
OutputFull text, timed segments, detected language
Max duration10 minutes
ExecutionSync
IdempotencyRequires Idempotency-Key header

Related Models