canonical: https://jentic.com/apis/bulktranscripts.co/bulktranscripts # BulkTranscripts API The BulkTranscripts API retrieves YouTube transcripts and searches YouTube videos, channels, and playlists. It fetches a single video's transcript, searches across YouTube or within one channel's uploads, and lists a channel's videos, its latest uploads, or a playlist's videos in order. A bulk operation starts a background job that fetches every transcript in a channel, playlist, or video list, and companion operations report the job's progress and per-video outcomes. The account operation reports the caller's current credit balance. ## For AI agents Fetch YouTube transcripts, search videos, channels, and playlists, and run bulk transcript jobs, across 10 endpoints secured with a bearer token or X-API-Key. ## Scope Does not host, transcode, or stream video, and does not generate speech-to-text itself. Use for retrieving existing YouTube transcripts and video search only. ## Capabilities - Fetch a single YouTube video's transcript - Search YouTube for videos, channels, or playlists, and search within one channel's uploads - List a channel's videos, its latest uploads, or a playlist's videos in order - Start a bulk job that fetches every transcript in a channel, playlist, or video list and poll its progress - Read the caller's current credit balance ## Use cases ### Transcript Retrieval and Search Turn a YouTube URL or search into readable text for an agent to summarise. The agent searches YouTube or a single channel, lists a channel's or playlist's videos, and fetches each video's transcript. Because transcripts are returned as structured text, the agent can quote and summarise them without scraping the page. Example prompt: Search YouTube for a topic, pick a video, and fetch its transcript ### Bulk Channel and Playlist Transcription Pull an entire channel or playlist in one background job. The agent starts a bulk job over a channel, playlist, or video list, polls the job's progress, and reads the per-video outcomes page to see which transcripts landed in the library. This is how an agent builds a corpus without fetching one URL at a time. Example prompt: Start a bulk job for a channel, poll its progress, then read the per-video results page ### AI Agent Integration via Jentic An AI agent discovers and calls BulkTranscripts through Jentic without handling the API key directly. The agent searches by intent, receives the matching operation and its input schema, and fetches a transcript or starts a bulk job while Jentic injects the stored key. This gives the agent YouTube text without reading the reference docs or holding secrets. Example prompt: Search Jentic for 'get a youtube transcript', load the operation schema, and fetch the transcript with Jentic-injected credentials ## Key endpoints | Method | Path | Description | | --- | --- | --- | | GET | `/api/v1/transcript` | Get a video's transcript | | GET | `/api/v1/search` | Search YouTube videos, channels, or playlists | | GET | `/api/v1/channel/videos` | List a channel's videos | | GET | `/api/v1/playlist/videos` | List a playlist's videos in order | | POST | `/api/v1/bulk` | Start a bulk transcript job for a channel, playlist, or video list | | GET | `/api/v1/bulk/{run_id}` | Check a bulk job's progress | ## Key resources - **Transcript** — Fetch a single video's transcript - **Search** — Search YouTube or within one channel, and list channel or playlist videos - **Bulk** — Start a bulk transcript job and read its progress and per-video outcomes - **Account** — Read the caller's current credit balance ## 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:** 64 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 99 / 100 - Developer Experience & Jentic Compatibility: 63 / 100 - AI-Readiness & Agent Experience: 46 / 100 - Agent Usability: 94 / 100 - Security: 55 / 100 - AI Discoverability: 60 / 100 - **View full report:** https://jentic.com/apis/bulktranscripts.co/bulktranscripts/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 BulkTranscripts by hand means creating a key, deciding whether to send it as a Bearer token or in the X-API-Key header, and tracking credit spend per transcript yourself. Through Jentic you install once, import BulkTranscripts from the API Directory, store the key once, and your agent calls it. - **Permission scoping:** Through Jentic you limit the agent to the read operations it needs, such as fetching transcripts and searching, while leaving the bulk job operations that spend more credits out of the set. - **Credential handling:** Your BulkTranscripts 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 transcript' or 'search youtube videos', and Jentic returns the matching BulkTranscripts operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **AssemblyAI** — Speech-to-text that transcribes your own audio, versus BulkTranscripts retrieving existing YouTube transcripts. - **Deepgram** — Real-time and batch speech-to-text, versus BulkTranscripts' YouTube-specific transcript retrieval. - **YouTube Data API** — YouTube metadata and channel data to pair with BulkTranscripts' transcript text. ## FAQ ### What authentication does the BulkTranscripts API use? The BulkTranscripts API authenticates with an API key, sent either as a Bearer token in the Authorization header or in the X-API-Key header, per its OpenAPI spec; a license key or an OAuth access token also works as a Bearer token. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never reaches the agent. ### Is there a BulkTranscripts MCP server? You do not need a separate MCP server to give your agent BulkTranscripts. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls its transcript and search operations on demand. Operations are discovered as needed, so no extra server's tool definitions load into the agent's context. ### Can I fetch an entire channel's transcripts with the BulkTranscripts API? Yes. Start a bulk job over a channel, playlist, or video list, poll the job for progress, and read the per-video outcomes page as transcripts land in your library. For a single video, fetch its transcript directly instead. ### Can I limit what my agent is allowed to do with the BulkTranscripts API? Yes. Because you run Jentic One yourself, your rules decide which BulkTranscripts operations the agent may call. You can allow the read operations it needs, such as fetching transcripts and searching, while withholding the bulk job operations that spend more credits, and every call is logged. ### What are the rate limits for the BulkTranscripts API? The spec documents an overall ceiling of 120 requests per minute per IP, alongside per-key limits; a transcript costs one credit the first time it enters your library, while repeat reads from your own library are free. Check the BulkTranscripts documentation at https://bulktranscripts.co for current per-plan limits. ### How do I get a YouTube transcript with the BulkTranscripts API through Jentic? Search Jentic for 'get a youtube transcript' to get the matching BulkTranscripts operation and its input schema, then your agent passes the video and reads the returned transcript text. To run it on your own infrastructure, install Jentic One from its GitHub repo.