canonical: https://jentic.com/apis/transcriptapi.com/transcriptapi

# TranscriptAPI

YouTube Transcript API with search, channel browsing, and playlist capabilities. The API exposes 4 endpoints secured with bearer authentication.

## For AI agents

Programmatically get youtube video transcript, search youtube. Covers 4 operations with bearer authentication.

## Scope

Does not handle payments, communications, or crm - use for ai and machine learning only.

## Capabilities

- Get YouTube video transcript
- Search YouTube
- List all videos from a YouTube channel
- Query and filter TranscriptAPI records by parameters
- Monitor TranscriptAPI operational status and events

## Use cases

### AI and Machine Learning Operations

Use the TranscriptAPI to perform ai ml operations programmatically. The API provides 4 endpoints covering core functionality including get youtube video transcript, search youtube, search within a youtube channel.

Example prompt: Call GET `/api/v2/youtube/transcript` to get youtube video transcript

### Automated Channels Management

Automate channels operations by combining multiple TranscriptAPI endpoints. Agents can search youtube and then search within a youtube channel in a single workflow.

Example prompt: Call GET `/api/v2/youtube/search` to search youtube, then verify the result

### AI Agent Integration via Jentic

AI agents discover and call TranscriptAPI endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle bearer tokens manually.

Example prompt: Search Jentic for 'get youtube video transcript', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/api/v2/youtube/transcript` | Get YouTube video transcript |
| GET | `/api/v2/youtube/search` | Search YouTube |
| GET | `/api/v2/youtube/channel/search` | Search within a YouTube channel |
| GET | `/api/v2/youtube/channel/videos` | List all videos from a YouTube channel |

## Key resources

- **Channels** — Operations related to Channels
- **Search** — Operations related to Search
- **Transcripts** — Operations related to Transcripts

## Why Jentic

- **Setup:** Wiring TranscriptAPI by hand means setting up its bearer token auth against transcriptapi.com and handling error responses yourself. Through Jentic you install once, import TranscriptAPI from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** TranscriptAPI is read-only, with the YouTube target passed as a query rather than an owned resource id in the URL path, so scope the agent to the operations it needs, such as fetching a transcript or searching videos, and leave out anything the workflow does not require. Every operation you allow is one you have chosen.
- **Credential handling:** Your TranscriptAPI token 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 a channel's videos', and Jentic returns the matching TranscriptAPI operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Openai** — Alternative ai ml API
- **Anthropic** — Alternative ai ml API
- **Cohere** — Complementary ai ml API
- **Huggingface** — Complementary ai ml API

## FAQ

### What authentication does the TranscriptAPI use?

The TranscriptAPI uses a Bearer token in the Authorization header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I get youtube video transcript with the TranscriptAPI?

Yes. Use the GET `/api/v2/youtube/transcript` endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the TranscriptAPI?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I get youtube video transcript through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'get youtube video transcript'. Jentic returns the matching TranscriptAPI operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the TranscriptAPI have?

The TranscriptAPI exposes 4 endpoints covering channels, search, transcripts operations.

### Can I limit what my agent is allowed to do with the TranscriptAPI?

Yes. TranscriptAPI is read-only, and in your self-hosted Jentic One instance your own rules decide which of its operations the agent may call, so you can allow only what a given workflow needs, such as fetching a transcript with GET `/api/v2/youtube/transcript` or searching with GET `/api/v2/youtube/search`, while leaving out channel listing and channel search. Because the YouTube target is passed as a query parameter rather than an owned resource id in the path, every operation you enable is one you have deliberately chosen. The stored bearer token is injected only when an allowed operation runs.