Start building

YouTube Transcript

agentbody/youtube-transcript

Extract text and timed segments from an existing YouTube manual or automatic subtitle track.. Supports language selection for multilingual videos.

Use in agentGet API key
Base price
$0.01 / run
Execution
sync
Model type
api
Input fields
2

Try the model

Playground

Open playground
Input
The YouTube video URL to extract subtitles from.
Requested subtitle language code (e.g. en, zh, ja). If omitted, returns the default track.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.01 / run
Billing formula
0.01

Context & modalities

Input
Schema-defined
Output
api

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
Agent Body
Model ID
agentbody/youtube-transcript
Execution
sync
API
Unified Run API
Endpoint
/v1/run

API README

YouTube Transcript

Extract text and timed segments from an existing YouTube manual or automatic subtitle track. Supports language selection for multilingual videos. It is suitable for subtitles, transcript, youtube workflows.

Capability

Extract text and timed segments from an existing YouTube manual or automatic subtitle track. Supports language selection for multilingual videos. It helps applications, agents, and automated workflows turn that capability into repeatable tasks and useful downstream experiences.

Common use cases

  • Collect and normalize information from public pages or source content for downstream workflows.
  • Build media monitoring, content intelligence, and publishing-support workflows.
  • Create repeatable integrations that pass structured results to downstream business systems.

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Endpoint
https://api.sandbase.ai/v1/run
Model ID
agentbody/youtube-transcript
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "agentbody/youtube-transcript"
}
SANDBASE_JSON
)
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
YouTube TranscriptThis model
Agent Body		———Jan 1, 2025
Document Parse
Agent Body		———Jan 1, 2025
Humanize Writing
Agent Body		———Jan 1, 2025
LinkedIn Email
Agent Body		———Jan 1, 2025
LinkedIn Phone
Agent Body		———Jan 1, 2025
LinkedIn Profile
Agent Body		———Jan 1, 2025