Skip to main content
Glama

TikTok Transcript

social_tiktok_video_transcript
Read-only

Extracts existing transcripts, captions, or subtitles from a TikTok video by URL. Returns id, url, and transcript (native captions are WEBVTT-formatted; AI fallback returns text). Also includes top-level transcript_with_timestamp: an array of {start: number, end: number, text: string} sentence/phrase segments from native captions or AI, or null when speech or timing is unavailable. Times are seconds relative to the video. AI timings are approximate, not word-perfect. The existing transcript remains the exact raw WEBVTT string for native captions and a plain string for AI fallback. No new parameter is required, and pricing is unchanged. Native transcripts cost 1 credit only when returned, with no fixed length limit; no transcript costs 0 credits. AI fallback is opt-in via use_ai_as_fallback=true and is used only when native captions are unavailable. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This dedicated transcript route charges the AI rate instead of adding a native-caption fee. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Get native captions or an opted-in AI transcript from a TikTok video. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Completed lookups cost at least 10 Nexscope credits. Actual cost depends on the operation and requested options. Repeated requests may purchase data again. TikTok Transcript API View Pricing Get native captions or an opt-in AI transcript with timestamp segments from a TikTok video. Long AI transcripts may time out. Native captions or AI up to 2 minutes: 1 credit. Paid AI mode: 10 credits/minute, rounded up, even for short videos. No transcript: 0 credits. Extracts existing transcripts, captions, or subtitles from a TikTok video by URL. Returns id, url, and transcript (native captions are WEBVTT-formatted; AI fallback returns text). Also includes top-level transcript_with_timestamp: an array of {start: number, end: number, text: string} sentence/phrase segments from native captions or AI, or null when speech or timing is unavailable. Times are seconds relative to the video. AI timings are approximate, not word-perfect. The existing transcript remains the exact raw WEBVTT string for native captions and a plain string for AI fallback. No new parameter is required, and pricing is unchanged. Native transcripts cost 1 credit only when returned, with no fixed length limit; no transcript costs 0 credits. AI fallback is opt-in via use_ai_as_fallback=true and is used only when native captions are unavailable. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This dedicated transcript route charges the AI rate instead of adding a native-caption fee. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Get native captions or an opted-in AI transcript from a TikTok video. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Paid opt-in, enabled only by the literal query value 'true' (allow_long_transcription=true). Defaults to false when omitted; other values do not enable paid mode. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This flag does not force AI and does not enable transcription or AI fallback by itself. Keep get_transcript=true or use_ai_as_fallback=true where required by the endpoint. Returned native captions still cost 1 credit on dedicated transcript routes, even for long videos with this flag; on detail routes they leave the base price unchanged. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Set to 'true' to use paid AI only when existing captions are unavailable. Defaults to false. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed. Native or default successful AI <=120s: 1; no transcript 0. Long AI mode must be explicitly enabled in addition to transcription; all successful AI, including short, costs 10 per started minute. See parameters for flags.

Input Schema

NameRequiredDescriptionDefault
urlYesTikTok video URL
languageNoLanguage of the transcript. 2 letter language code, ie 'en', 'es', 'fr', 'de', 'it', 'ja', 'ko', 'zh'
use_ai_as_fallbackNoSet to 'true' to use paid AI only when existing captions are unavailable. Defaults to false. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed.
allow_long_transcriptionNoPaid opt-in, enabled only by the literal query value 'true' (allow_long_transcription=true). Defaults to false when omitted; other values do not enable paid mode. By default, successful AI transcription of videos up to 120 seconds (two minutes, inclusive) costs a flat 1 credit per request. Over 120 seconds, videos cannot be AI-transcribed by default. Set allow_long_transcription=true to opt into paid AI with no fixed duration cap: ALL successful AI transcriptions in this mode cost 10 credits per started minute, including short videos: 10 * ceil(duration_seconds / 60). For example, 177 seconds costs 30 credits and an opted-in 60 seconds costs 10 credits. Empty AI results and errors cost 0 credits for AI transcription. This flag does not force AI and does not enable transcription or AI fallback by itself. Keep get_transcript=true or use_ai_as_fallback=true where required by the endpoint. Returned native captions still cost 1 credit on dedicated transcript routes, even for long videos with this flag; on detail routes they leave the base price unchanged. These routes remain synchronous. Allow at least 30 seconds on your client. Paid long transcription can exceed resource limits or timeouts, so successful transcription of long videos is not guaranteed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/openWorld annotations, the description discloses the synchronous nature of the call, a recommended client timeout of 30 seconds, the risk that long paid transcription may exceed resource limits, and the exact WEBVTT vs plain-text return formats. That is substantial behavioral context, though it is buried in heavy repetition and references a parameter (get_transcript=true) that does not exist in this schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description repeats the identical pricing paragraph at least five times and then repeats the entire body verbatim again, roughly tripling its necessary length. The actual signal (what it returns, the two opt-in flags, cost tiers) is buried in duplication, and the front-loaded purpose statement is the only well-structured part.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description does cover return shape (id, url, transcript, transcript_with_timestamp and its segment object) and the null-when-no-timing case, which is genuinely useful. But the constant repetition and the stray references to 'detail routes' and get_transcript=true leave an agent with confusing, partly irrelevant context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains url, language, use_ai_as_fallback and allow_long_transcription. The description restates the same flag semantics rather than adding anything new, so baseline 3 applies; the cross-reference to a non-existent get_transcript flag is noise rather than added meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb and resource: 'Extracts existing transcripts, captions, or subtitles from a TikTok video by URL', and it enumerates the returned fields. It is clear to an agent what the tool does, but it never distinguishes itself from siblings such as social_tiktok_video or social_youtube_transcript.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains that AI fallback is opt-in and used only when native captions are unavailable, and that long transcription requires an explicit opt-in flag, which is real usage guidance. However, there is no statement of when to pick this tool over social_tiktok_video (which likely returns a transcript too) or over the other transcript siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.