Instagram Transcript API
Turn any Instagram Reel's speech into text — the full transcript plus timestamped segments, ready for search, subtitles, or AI pipelines.
Send a Reel URL and the Instagram Transcript API returns everything spoken in the video as clean text: the full transcript, timestamped segments (start time and duration for each line), and word count. Auto-detects the spoken language, or pass an optional language code (like 'tr' or 'en') to pin it — recommended for short clips. A photo or photo carousel is 422 not_a_video (retryable false, 0 credits) with suggestedEndpoint /v1/instagram/details — not a 502. Mixed carousels transcribe a video slide; img_index selects that slide when present. Great for making Reels searchable, generating subtitles, feeding AI tools, or turning video into text. No Instagram login or OAuth required. Pass cache=true to serve from the 24h shared cache (0 credits on hit); default is always fresh.
Request
- Base URL: https://api.captapi.com
- URL: https://api.captapi.com/v1/instagram/transcript
- Auth: one of:
- HTTP bearer
- API key in header X-API-Key
Query parameters
Instagram Reel URL, e.g. https://instagram.com/reel/ID/. The URL platform must match this endpoint's platform. Do not pass cross-platform URLs, e.g. YouTube to TikTok, Instagram to Facebook, LinkedIn to X/Twitter, or Pinterest to Rumble.
Preferred caption language as an ISO code, e.g. "en". Defaults to auto-detect.
Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh.
Response
Success. The data object for this endpoint.
Changes
No recorded changes to this operation across all 3 revisions of this API.