tubetext/tiktok-transcript
tubetext--tiktok-transcriptDestructive
This tool calls the Actor "tubetext/tiktok-transcript" and retrieves its output results. Actor description: Get TikTok video transcripts from video or share links. Returns transcript text, timestamps, SRT and video stats, from TikTok captions or Whisper AI when there are none. $0.0015 per transcript (+$0.006/AI minute); music-only and failed videos are free. · by TubeText
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| urls | No | Provide at least one of: urls / datasetId. TikTok video links (https://www.tiktok.com/@user/video/123…), share links from the app (tiktok.com/t/…, vm.tiktok.com/…) or numeric video IDs. One per line, as many as you like. Example values: ["https://www.tiktok.com/@hermoneymastery/video/7691028177199680781","https://www.tiktok.com/@beatrizcontreras31/video/7691869739597024542"] | |
| waitSecs | No | Max seconds (0–45, default 30) to cap the wait for the Actor run to reach terminal state. For long-running Actors the response returns at the cap with the current run status; follow `nextStep` to poll via get-actor-run. Set to 0 to fire-and-forget. | |
| datasetId | No | A dataset from another Actor run, e.g. a TikTok profile, hashtag or trending scraper (pick it, or paste its ID via API). The TikTok video links in it are transcribed. Read-only access to this one dataset is requested. | |
| languages | No | Optional language codes in order of preference (e.g. en, es). TikTok sometimes offers translated captions. Empty = the video's original language. | |
| chunkWords | No | Set e.g. 300 to add a 'chunks' array: transcript split into ~N-word blocks with start/end timestamps. 0 = off. | |
| includeSrt | No | Adds an 'srt' field in SubRip (.srt) format. | |
| datasetSortBy | No | Which videos to take first when the dataset has more than 'Max videos from dataset'. Example values: "views" | views |
| maxConcurrency | No | How many videos to process in parallel. Example values: 10 | |
| aiTranscription | No | Videos without TikTok captions are transcribed with Whisper AI. Charged per started minute of audio, only when real speech is found – music-only videos are free. Example values: "missing" | missing |
| includeSegments | No | Adds a 'segments' array with start, duration and text. | |
| transcribeMusic | No | By default, caption-less videos that use a song or another creator's sound are treated as music and skipped (free). Turn on to transcribe lyrics too. | |
| maxAiMinutesPerVideo | No | Longer videos are skipped by AI transcription to keep costs predictable. Example values: 60 | |
| maxVideosFromDataset | No | How many video links to take from the dataset (each is billed like a single video). Example values: 50 | |
| includeTimestampedText | No | Adds a 'timestampedText' field with one [mm:ss] line per sentence. Example values: true |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tip | No | Advisory guidance RAG Web Browser wrote to its key-value store under the reserved "TIP" key | |
| runId | Yes | Actor run ID | |
| stats | No | Run statistics | |
| status | Yes | Run status: READY | RUNNING | TIMING-OUT | TIMED-OUT | ABORTING | ABORTED | SUCCEEDED | FAILED | |
| actorId | Yes | Stable Apify Actor ID from the run record | |
| summary | Yes | Past-tense summary of the run state | |
| exitCode | No | Actor process exit code; populated for terminal states (especially FAILED) | |
| nextStep | Yes | One primary follow-up action with identifiers interpolated | |
| storages | Yes | Dataset and key-value store metadata, keyed by alias. "default" is always the primary entry. | |
| actorName | No | "username/actor-name" | |
| startedAt | No | ISO timestamp when the run started | |
| finishedAt | No | ISO timestamp when the run finished (terminal states only) | |
| statusMessage | No | Pass-through from Apify run.statusMessage | |
| apifyConsoleUrl | No | Personalized Apify Console link to the run; present only for Console sessions |