canonical: https://jentic.com/apis/getyoutubetranscript.com/getyoutubetranscript # GetYouTubeTranscript API The GetYouTubeTranscript API returns the caption transcript of any YouTube video and exposes the surrounding metadata an agent needs to find the right video first. It searches YouTube for videos or channels, resolves a channel handle or URL to a channel ID, lists every video in a playlist or on a channel, and reports a video's available caption languages. Successful requests spend one credit each, failed and rate-limited requests are never charged, and a batch endpoint queues transcripts for up to 100 videos at once. ## For AI agents Fetch YouTube video transcripts and caption languages, search videos and channels, resolve channel handles, and list playlist or channel videos. Includes a batch endpoint for up to 100 videos per request. ## Scope Does not upload videos, manage YouTube channels, or run ad campaigns. Use for reading YouTube transcripts, search results, and channel or playlist data only. ## Capabilities - Retrieve the full transcript of a YouTube video by URL or video ID - List the caption languages available for a given video - Search YouTube for matching videos or channels - Resolve a channel handle or URL to its channel ID - List every video in a playlist or uploaded by a channel - Queue transcripts for up to 100 videos in a single batch request - Check the remaining credit balance for the active key ## Use cases ### Agent-driven video research An AI agent researching a topic searches YouTube for relevant videos, resolves the best channel, and pulls each video's transcript so it can summarise or quote the spoken content. The GetYouTubeTranscript API returns transcripts plus the search and channel metadata needed to pick sources, and through Jentic the agent discovers and calls these operations by intent without hand-wiring the key. Example prompt: Search YouTube for the three most relevant videos on a topic, fetch each transcript, and return a sourced summary ### Bulk transcript extraction Content teams that need transcripts for a large archive list a channel's uploads or a playlist and queue every video for transcript extraction in batches of up to 100. The batch endpoint returns a job that can be polled for status and paged results, so a pipeline can process a whole channel without issuing one request per video. Example prompt: List every video in a playlist and queue all of them for transcript extraction in a single batch, then poll until the job completes ### Caption language discovery Before requesting a transcript an agent checks which caption languages a video provides, then fetches the transcript in the language the user asked for. This avoids wasted calls on videos with no captions and lets a localisation workflow pick the correct source language for translation. Example prompt: List the caption languages for a video and fetch the transcript in English if it is available ## Key endpoints | Method | Path | Description | | --- | --- | --- | | GET | `/transcript` | Get a YouTube video transcript | | GET | `/transcript/languages` | List a video's caption languages | | GET | `/search` | Search YouTube videos or channels | | GET | `/playlist` | List every video in a playlist | | GET | `/channel/videos` | List every video a channel has uploaded | | POST | `/batch` | Queue transcripts for up to 100 videos | ## Key resources - **Transcript** — Fetch a video's transcript and list its available caption languages - **Search** — Search for videos or channels and resolve a channel handle to its ID - **Channel** — Read channel metadata, latest uploads, and the full list of a channel's videos - **Playlist** — List every video contained in a playlist - **Batch** — Queue transcripts for up to 100 videos and poll for status and results ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 61 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 76 / 100 - Developer Experience & Jentic Compatibility: 71 / 100 - AI-Readiness & Agent Experience: 41 / 100 - Agent Usability: 94 / 100 - Security: 55 / 100 - AI Discoverability: 64 / 100 - **View full report:** https://jentic.com/apis/getyoutubetranscript.com/getyoutubetranscript/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring the GetYouTubeTranscript API by hand means minting a key through its signup flow, choosing whether to send it as a bearer token or in the x-api-key header, and tracking credit spend yourself. Through Jentic you install once, import it from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** You choose which operations the agent may call, so a key that can read transcripts and search does not also have to expose the signup or batch-queueing operations unless you add them. GetYouTubeTranscript carries the video, channel, and playlist targets as query parameters rather than URL path ids, so rules bound which operations your agent runs. - **Credential handling:** Your GetYouTubeTranscript key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'get a YouTube video transcript' or 'search YouTube videos', and Jentic returns the matching operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Rev AI** — Rev AI transcribes audio and video with speech-to-text rather than reading existing YouTube captions. - **AssemblyAI** — AssemblyAI runs speech-to-text and audio understanding on arbitrary audio files. - **Vimeo** — Vimeo hosts and manages video content, where GetYouTubeTranscript only reads YouTube data. ## FAQ ### What authentication does the GetYouTubeTranscript API use? The GetYouTubeTranscript API accepts a key either as a bearer token or in the x-api-key header, per its OpenAPI spec. You get a key from the dashboard or through the self-service signup flow, and one credit is spent per successful request while failed and rate-limited requests are not charged. Through Jentic the key is stored once and injected at call time, so it never enters the agent's prompt or logs. ### Can I fetch transcripts for many videos at once with the GetYouTubeTranscript API? Yes. The batch endpoint queues transcripts for up to 100 videos in a single request and returns a job you can poll for status and a page of results. Combine it with the playlist or channel-videos listing to feed a whole channel into one batch instead of calling the transcript endpoint once per video. ### What are the rate limits for the GetYouTubeTranscript API? The OpenAPI spec does not define numeric rate limits; usage is metered in credits, where one credit is spent per successful request and rate-limited requests are never charged. See https://getyoutubetranscript.com/docs for current limits, and have your agent back off when it receives an HTTP 429 response. ### Is there a GetYouTubeTranscript MCP server? Yes, GetYouTubeTranscript offers an official MCP server. You can also connect the API directly through Jentic: your agent gets the full 13-endpoint surface without loading another server's tool definitions into its context, your credential is injected at call time by your self-hosted instance, and your rules decide which operations the agent may call. ### Can I limit what my agent is allowed to do with the GetYouTubeTranscript API? Yes. Write a rule that allows only the read operations your workflow needs, such as fetching transcripts and searching videos, so the agent can read captions and metadata but cannot touch the signup or batch-queueing operations unless you add them. Every call it makes is logged. ### How do I fetch a transcript through Jentic? Search Jentic for an intent such as 'get a YouTube video transcript' and it returns the matching transcript operation with its input schema, so your agent passes the video URL or ID and reads back the caption text. To run it on your own infrastructure, install Jentic One from its GitHub repo.