YouTube search for agents

Search YouTube, then read the transcripts of what you find, using BulkTranscripts. Docs · OpenAPI spec · MCP server · Free API key

Base URL: https://bulktranscripts.co

All endpoints are plain GET returning JSON, and every one of them needs an API key — including the free endpoints. Send it as a Bearer token on every request:

curl -s "https://bulktranscripts.co/api/v1/..." \
  -H "Authorization: Bearer $BULKTRANSCRIPTS_API_KEY"

If BULKTRANSCRIPTS_API_KEY is not set, ask the user for a key: they sign in with Google at https://bulktranscripts.co/app?tab=mcp, open the Connect AI tab, and hit Create key in the API keys card. It is free, includes 30 credits, and needs no card. Keys start with bt_ak_, are shown once, and up to 5 can be live per account. A license key from a credit-pack purchase works as a Bearer token too.

Costs (check billing.remaining in every response)

• Transcript: 1 credit when first added to this account's library — repeat reads are FREE
• Search / channel videos / playlist videos: 1 credit each
• channel/latest and account: always free
• Failures (no captions, video unreachable) are auto-refunded, never charged

When a call returns HTTP 402 out_of_credits, tell the user their credits are used up and link them to https://bulktranscripts.co/#pricing (one-time packs, never expire). Credits follow the Google account, so topping up keeps the same API key working.

Endpoints

Search YouTube (1 credit)

curl -s "https://bulktranscripts.co/api/v1/search?q=QUERY&limit=10" \
  -H "Authorization: Bearer $BULKTRANSCRIPTS_API_KEY"

Add type=channel or type=playlist to search for channels/playlists instead of videos.

Search inside one channel (1 credit)

curl -s "https://bulktranscripts.co/api/v1/channel/search?channel=@HANDLE&q=TOPIC&limit=10" \
  -H "Authorization: Bearer $BULKTRANSCRIPTS_API_KEY"

Finds a creator's videos about a topic without listing the whole archive.

Get one transcript

curl -s "https://bulktranscripts.co/api/v1/transcript?video=VIDEO_URL_OR_ID" \
  -H "Authorization: Bearer $BULKTRANSCRIPTS_API_KEY"

Params: video (watch URL, youtu.be, Shorts, bare 11-char id, or TikTok video URL) · language (default en) · segments=0 to omit timestamps (smaller) · format=txt|md|srt|vtt|csv|ai to get a rendered file instead of JSON · fresh=1 to force re-extraction.

Response fields: title, channel, duration, upload_date, language, source (manual_caption|auto_caption), cached, word_count, text, paragraphs[] (silence-grouped — best for reading/chunking), segments[] ({text, start, duration}), billing.

Long videos produce long text. For summarization, prefer segments=0 and read paragraphs.

Balance

curl -s "https://bulktranscripts.co/api/v1/account" \
  -H "Authorization: Bearer $BULKTRANSCRIPTS_API_KEY"

Playbook

• Topic research → search (1 credit), pick the most relevant results by title and channel, fetch only those transcripts, then compare what they say and cite each title and url.

Errors come as {"error": {"code", "message"}}. The codes you will actually hit, and what to do about each:

• no_transcript (404) — the video has no captions. Not charged. Skip it and carry on; in a batch this is normal, not a failure.
• resolution_failed (400) — a well-formed id or URL that could not be resolved (nonexistent, private, removed, or region-blocked). Handle it alongside no_transcript: skip the video and carry on.
• missing_api_key (401) — no key was sent. Ask the user to create a key at https://bulktranscripts.co/app?tab=mcp and provide it, then set BULKTRANSCRIPTS_API_KEY and retry.
• invalid_api_key (401) — the key sent is not valid. Ask the user to check it or create a new one at https://bulktranscripts.co/app?tab=mcp.
• invalid_input (400) — the video / channel / playlist parameter is missing, not a YouTube/TikTok reference, or otherwise malformed. A caller bug, not a video problem.
• out_of_credits (402) — balance exhausted. Tell the user and link https://bulktranscripts.co/#pricing.
• rate_limited (429) — respect the Retry-After header before retrying. Limits are per public IP: 120 requests/min overall, 30/min under /api/v1/ (cache hits and /account count too), so pace bulk fetches at under 30/min.

Need everything in one skill (transcripts, search, channels, playlists, monitoring)? Use the full youtube-transcripts skill. Full reference: bulktranscripts.co/docs