Approved content archives
Save searchable transcripts for brand-owned or otherwise permitted TikTok assets in an internal library.
TikTok transcription API for public videos
Connect public TikTok videos to a dependable transcription job lifecycle. Fast Transcriber accepts canonical video URLs and still-valid public share links, then returns a source-independent JSON result for your application.
Use it from your product backend or connect a compatible AI agent over MCP.
- Bearer authentication
- Asynchronous jobs
- Structured JSON
Queue a canonical TikTok video URL
curl --include --request POST https://fast-transcriber.com/api/v1/transcriptions \
--header "Authorization: Bearer $FAST_TRANSCRIBER_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"source_url": "https://www.tiktok.com/@creator/video/1234567890123456789",
"speaker_diarization": false
}'202 Accepted · Location: /api/v1/transcriptions/{id}
Turn TikTok speech into structured product data
Canonical tiktok.com/@creator/video/{id} URLs are the most durable input for logging and deduplication. Public vm.tiktok.com and vt.tiktok.com share links can also be submitted while their redirect chains remain active.
Store the canonical video ID when your workflow knows it. Short links can be shared many times for the same video and can expire; a stable identity prevents duplicate jobs and makes future retrieval easier.
With Fast Transcriber
- One asynchronous job lifecycle across supported sources
- Source resolution and media retrieval handled server-side
- One transcript response with text and timestamped segments
- A direct-upload fallback for authorized private media
Building every source yourself
- Separate URL and access handling for every source
- Queue, retry, polling, and failure-state infrastructure
- Source-specific results that need normalization
- Ongoing maintenance as external sources change
One API family
One source workflow. One predictable job model.
Use the same status lifecycle and transcript fields across supported public URLs and account-owned uploads.
What this endpoint accepts
Supported inputs
- Public canonical TikTok video URLs
- Still-valid vm.tiktok.com share links
- Still-valid vt.tiktok.com share links
- One public video per request
Access and input boundaries
- The video and every redirect must remain accessible without cookies or an account.
- Profiles, sounds, hashtags, feeds, and collections are not individual media inputs.
- Removed, private, age-restricted, or region-restricted videos may not resolve.
- Avoid repeatedly queueing a short link that no longer redirects to available media.
Queue once, then follow the job
Transcription runs outside the original HTTP request. Save the returned job identity and poll its status instead of submitting duplicate work.
- 01
Send one TikTok URL
POST source_url to /api/v1/transcriptions with a bearer API key. Create one job for each media item.
- 02
Save the job location
A valid request returns 202 Accepted. Persist the Location header and job ID instead of repeating the POST.
- 03
Poll to a final state
GET the job URL with bounded backoff until status is completed or failed, then stop polling.
Built for production transcription workflows
Review queues
Let reviewers read speech first and jump to relevant moments using timestamped segment boundaries.
Creator productivity
Give creators an editable text draft that can support captions, summaries, and cross-channel reuse.
Send a real API request
Authenticate from your backend, create the job, and store the returned Location header for status retrieval.
Queue a canonical TikTok video URL
curl --include --request POST https://fast-transcriber.com/api/v1/transcriptions \
--header "Authorization: Bearer $FAST_TRANSCRIBER_API_TOKEN" \
--header "Content-Type: application/json" \
--data '{
"source_url": "https://www.tiktok.com/@creator/video/1234567890123456789",
"speaker_diarization": false
}'202 Accepted · Location: /api/v1/transcriptions/{id}
Implement the complete request flow
Authentication, source rules, request fields, and status handling are covered in the technical guide.
One predictable transcript response
TikTok output follows the normal Fast Transcriber result contract. Read data.text for the complete transcript and data.segments for time-aware interfaces or downstream processing.
- status
- Use completed and failed as terminal states.
- text
- The complete transcript becomes available on completion.
- segments[]
- Each segment includes start, end, and text values.
- duration_seconds
- The detected duration of the processed recording.
application/json
{
"data": {
"id": "95c3fdd8-...",
"filename": "source-media.mp4",
"status": "completed",
"created_at": "2026-08-24T16:30:00.000Z",
"duration_seconds": 1842,
"text": "Completed transcript text...",
"segments": [
{ "start": 0, "end": 4.2, "text": "Welcome." }
]
}
}200 OK · completed transcript
TikTok API FAQ
- Do TikTok short links work?
- vm.tiktok.com and vt.tiktok.com links can be submitted while they still redirect publicly to one available TikTok video.
- Can I submit a TikTok profile or sound page?
- No. source_url must identify one video. Profile, sound, hashtag, and feed pages are not individual media jobs.
- Should my application store the short URL?
- You can retain it for provenance, but a canonical video URL or ID is better for detecting repeated shares of the same media.
- Can the API use my TikTok account session?
- No. Public source processing does not accept your TikTok cookies. Use file upload for authorized media that is not publicly available.
Related endpoints
API overviewUse the same job model elsewhere
Ready to build?
Add TikTok transcription to your product.
Create a key, then follow the source guide to queue your first job.