Skip to main content
Glama

get_video_transcript

Retrieve a YouTube video transcript with timestamps for quoting and citing. Filter by time range to focus on specific segments, using public caption tracks at no API cost.

Instructions

Get a video's transcript as '[MM:SS] text' lines you can quote and cite.

Quote the timestamps back so claims stay traceable, e.g. "at [03:15] he says the battery is 17% larger than last year". Narrow long videos with start_seconds and end_seconds. Reads public caption tracks, so it costs no API quota.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
videoYesVideo id, or a watch / youtu.be / shorts URL
languagesNoPreferred language codes in priority order, e.g. ['en', 'en-US']; defaults to the video's original spoken language
end_secondsNoOnly return the transcript up to this offset
chunk_secondsNoMerge caption cues into windows of about this many seconds; 0 keeps raw cues
start_secondsNoOnly return the transcript from this offset onward

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesCanonical watch URL
textYesTranscript as '[MM:SS] text' lines, one per merged segment
languageYesTranscript language name
video_idYesVideo id
end_secondsYesEnd offset of the last returned line
is_generatedYesTrue when auto-generated by YouTube rather than creator-supplied
language_codeYesTranscript language code, e.g. en
segment_countYesNumber of timestamped lines returned
start_secondsYesOffset of the first returned line
available_languagesNoLanguage codes with a transcript for this video
Behavior4/5

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

With no annotations provided, the description discloses key behaviors: returns timestamped text lines, supports slicing via start/end, reads public caption tracks, and costs no API quota. It adds value beyond the schema by explaining the quote-and-cite workflow and the cost implication, though it omits edge cases like missing captions or language fallback.

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

Conciseness5/5

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

The description is four sentences, front-loaded with the core purpose, then usage tips and cost note. Every sentence adds functional or practical value without redundancy or filler.

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

Completeness4/5

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

Given no annotations but an output schema and 5 parameters, the description covers purpose, usage, and behavioral context adequately. It omits failure modes or return structure, but the output schema presumably handles the latter. For a read-only tool with this complexity, the description is reasonably complete.

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 coverage is 100%, so baseline is 3. The description mentions start_seconds and end_seconds for narrowing videos and hints at timestamp usage, but does not add meaning for languages or chunk_seconds beyond what the schema already provides. It adds moderate value but doesn't fully compensate with extra parameter context.

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

Purpose5/5

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

The description clearly states it gets a video's transcript formatted as '[MM:SS] text' lines for quoting and citing. It distinguishes from sibling tools (find_channel, search_channel_videos, etc.) by focusing on transcript retrieval, a distinct resource and action.

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

Usage Guidelines4/5

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

The description provides clear usage context: quote timestamps back for traceability, use start_seconds/end_seconds to narrow long videos, and note that it reads public caption tracks so no API quota is consumed. It does not explicitly exclude alternatives or mention when not to use, but the guidance is specific and practical.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/guyvandam/yt-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server