Getting Started with Transcript Bunny

Welcome to Transcript Bunny. Get transcripts from public YouTube videos that have captions.

What is Transcript Bunny?

Transcript Bunny is a powerful tool that extracts transcripts from YouTube videos instantly. Whether you're a content creator, researcher, student, or developer, we make it easy to get accurate transcripts with timestamps, AI summaries, and more.

Key Features

  • Instant Transcripts: Get transcripts in seconds with accurate timestamps
  • AI Summaries: Generate structured summaries with key points and takeaways
  • Chat with Videos: Ask questions about the video content using AI
  • Multiple Formats: Download as TXT, JSON, or SRT subtitle files
  • API Access: Integrate transcripts into your applications
  • Click-to-Jump: Click any timestamp to jump to that moment in the video

Quick Start

  • 1. Sign Up: Create a free account and get 15 credits/month
  • 2. Paste URL: Copy a public YouTube video URL with captions and paste it into the dashboard
  • 3. Get Transcript: Your transcript appears with timestamps
  • 4. Use AI Features: Generate summaries or chat with the video content
  • 5. Download: Export in your preferred format (TXT, JSON, SRT)

Creating Transcripts

How to Create a Transcript

  1. Navigate to Dashboard: Go to your dashboard from the main navigation
  2. Paste YouTube URL: In the "Create New Transcript" section, paste a public YouTube video URL with captions. Supported formats:
    • https://www.youtube.com/watch?v=VIDEO_ID
    • https://youtu.be/VIDEO_ID
    • https://m.youtube.com/watch?v=VIDEO_ID
  3. Click Create: Hit the "Create Transcript" button and your transcript will be processed
  4. View Progress: Most videos finish in a few seconds. Longer videos can take more time.

Credit Usage

The first time your account requests a video, it costs 1 credit, even if another account already has it stored. Replaying a transcript you already own is free. Failed requests do not consume credits.

Why Might a Transcript Fail?

  • Video doesn't have captions/subtitles enabled
  • Video is private or age-restricted
  • Channel has disabled transcript access
  • Temporary service issues

Managing Your Transcripts

Viewing Transcripts

Navigate to the Transcripts page to see all your transcripts. Completed transcripts are stored durably and normally remain available for account replay for a long time. There is currently no automatic expiration job; replay still requires the stored transcript to be available.

  • Search by video title or channel name
  • Filter by status (completed, processing, queued, failed)
  • Filter by channel
  • Switch between grid and list view
  • Click any transcript to view the full content

Click-to-Jump Feature

When viewing a transcript, you can click any timestamp to jump directly to that moment in the video. This makes it easy to:

  • Navigate to specific sections quickly
  • Verify transcript accuracy
  • Create video clips or highlights
  • Take notes with precise timestamps

Status Indicators

Completed Transcript is ready to view
Processing Currently being transcribed
Queued Waiting in queue to be processed
Failed Transcript couldn't be generated (no credit charged)

AI-Powered Features

AI Summary

Generate a structured summary of any video transcript with key points, main topics, and takeaways.

How to Use:

  1. Open any completed transcript
  2. Click the "AI Summary" tab
  3. The AI will analyze the content and generate a summary (10-15 seconds)
  4. Review the structured summary with key points and takeaways

What You Get:

  • Main topics and themes
  • Key points and insights
  • Important takeaways
  • Actionable conclusions

Pro Tip

AI summaries are perfect for long videos, lectures, or tutorials where you need a quick overview.

Chat with Video AI

Ask questions about the video content and get intelligent answers based on the transcript.

How to Use:

  1. Open any completed transcript
  2. Click the "Chat with Video AI" tab
  3. Type your question in the chat input
  4. Get instant answers based on the video content

Example Questions:

  • "What are the main points discussed?"
  • "Explain the concept of X mentioned in the video"
  • "What solutions were proposed for Y?"
  • "Summarize the section about Z"

Downloading Transcripts

Export your transcripts in multiple formats for different use cases.

Available Formats

TXT Format

Plain text format with timestamps. Perfect for:

  • Note-taking apps
  • Text editors
  • Documentation
  • Blog posts

JSON Format

Structured data format with metadata. Perfect for:

  • Developers and APIs
  • Data analysis
  • Custom applications
  • Integration workflows

SRT Format

Standard subtitle format. Perfect for:

  • Video editing software
  • Subtitle files
  • Media players
  • Accessibility

Open a completed transcript on the web app and use the download buttons there. Exports are available at /transcript/VIDEO_ID/download?format=txt|json|srt. The REST API returns JSON; it does not serve TXT or SRT files.

Plans & Billing

Available Plans

Free

$0/month
  • 15 credits/month
  • API & MCP access (5 req/min)
  • AI summaries and chat

Starter

$9/month
  • 1,000 credits/month
  • API & MCP access (50 req/min)
  • AI summaries and chat
POPULAR

Pro

$19/month
  • 3,000 credits/month
  • API & MCP access (100 req/min)
  • AI summaries and chat

Business

$49/month
  • 10,000 credits/month
  • API & MCP access (200 req/min)
  • AI summaries and chat

Annual Billing

Save 33% with annual billing - pay for 8 months, get 12 months!

How to Upgrade

  • 1. Navigate to Billing page
  • 2. Choose your plan (monthly or annual)
  • 3. Click "Upgrade to [Plan Name]"
  • 4. Complete checkout with Polar
  • 5. Start using your new credits immediately

Managing Your Subscription

From the Billing page, you can:

  • View current plan and usage
  • See billing period and renewal date
  • Upgrade or downgrade plans
  • Update payment method
  • Cancel subscription (access billing portal)

API Authentication

Learn how to authenticate your API requests with Transcript Bunny.

API Keys

Transcript Bunny uses API keys to authenticate requests. All API requests must include your API key in the Authorization header.

Available on All Plans

API keys are available on every plan, including Free. Free plan usage is limited to 5 requests/minute and your monthly credit balance. Upgrade for higher limits.

Creating an API Key

  • 1. Navigate to API Keys page
  • 2. Enter a name for your API key
  • 3. Click "Create API Key"
  • 4. Copy your key immediately (it won't be shown again)

API Key Format: Your API keys will look like this:

tb_live_...

API Key Management

You can revoke your API keys at any time from the API Keys page. API keys use your account credits.

Using Your API Key

Include your API key in the Authorization header of every request:

Authorization: Bearer YOUR_API_KEY

Security Best Practices

  • • Never share your API keys publicly
  • • Store keys securely as environment variables
  • • Rotate keys regularly
  • • Delete unused keys immediately

Get Transcript Endpoint

Retrieve transcripts for public YouTube videos that have captions, programmatically.

Endpoint

POST https://transcriptbunny.com/api/v1/transcribe

Request Body

{
"videoUrl": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"
}

Parameters

Parameter Type Required Description
videoUrl string Yes YouTube video URL
timestamps boolean No Set true to also receive transcript.timestampedText — the transcript as lines prefixed with [mm:ss] timestamps, ready to paste into an LLM prompt

Code Examples

const response = await fetch('https://transcriptbunny.com/api/v1/transcribe', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY'
},
body: JSON.stringify({
videoUrl: 'https://www.youtube.com/watch?v=dQw4w9WgXcQ'
})
});
const data = await response.json();
console.log(data);
import requests
response = requests.post(
'https://transcriptbunny.com/api/v1/transcribe',
headers={
'Content-Type': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY'
},
json={
'videoUrl': 'https://www.youtube.com/watch?v=dQw4w9WgXcQ'
}
)
data = response.json()
print(data)
<?php
$ch = curl_init('https://transcriptbunny.com/api/v1/transcribe');
curl_setopt_array($ch, [
CURLOPT_POST => true,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HTTPHEADER => [
'Content-Type: application/json',
'Authorization: Bearer YOUR_API_KEY'
],
CURLOPT_POSTFIELDS => json_encode([
'videoUrl' => 'https://www.youtube.com/watch?v=dQw4w9WgXcQ'
])
]);
$response = curl_exec($ch);
$data = json_decode($response, true);
print_r($data);
?>
require 'net/http'
require 'json'
uri = URI('https://transcriptbunny.com/api/v1/transcribe')
http = Net::HTTP.new(uri.host, uri.port)
http.use_ssl = true
request = Net::HTTP::Post.new(uri.path)
request['Content-Type'] = 'application/json'
request['Authorization'] = 'Bearer YOUR_API_KEY'
request.body = { videoUrl: 'https://www.youtube.com/watch?v=dQw4w9WgXcQ' }.to_json
response = http.request(request)
data = JSON.parse(response.body)
puts data
curl -X POST https://transcriptbunny.com/api/v1/transcribe \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{"videoUrl": "https://www.youtube.com/watch?v=dQw4w9WgXcQ"}'

Other Endpoints

Get a stored transcript

GET https://transcriptbunny.com/api/v1/transcripts/:videoId

Returns a transcript this account already owns. Optional query timestamps=true adds transcript.timestampedText. Does not charge credits. 404 if this account has not transcribed the video.

Usage

GET https://transcriptbunny.com/api/v1/usage

Returns plan, credits.total/used/remaining, request counts, and billingPeriod. Same Bearer authentication as transcribe.

Response Format

Understanding the API response structure.

Success Response

When a transcript is successfully retrieved, you'll receive 200 OK for an account replay (0 credits) or a global cache hit (1 credit if this account has not acquired it yet), or 201 Created for a fresh upstream fetch:

{
"transcript": {
"text": "Hello, welcome to this video. This is a sample transcript.",
"segments": [
{
"text": "Hello, welcome to this video.",
"start": 0.0,
"end": 3.5,
"timestamp": "00:00"
},
{
"text": "This is a sample transcript.",
"start": 3.5,
"end": 6.2,
"timestamp": "00:03"
}
]
},
"video": {
"id": "dQw4w9WgXcQ",
"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"title": "Example video",
"channelName": "Example Channel"
},
"source": "fetched",
"creditsCharged": 1,
"creditsRemaining": 999
}

Response Fields

Field Type Description
transcript object Transcript data with segments
transcript.text string Complete transcript as plain text
transcript.segments array Array of transcript segments with timestamps
transcript.timestampedText string Only when timestamps=true: transcript as [mm:ss]-prefixed lines (also on GET /api/v1/transcripts/:videoId?timestamps=true)
video object Video id, url, title, and channel name when available
source string fetched (new upstream fetch), global_cache (already stored for another account), or account_replay (this account already owns it)
creditsCharged number 0 for an account replay. 1 for a fresh fetch or a global cache hit for an account that has not requested this video before.
creditsRemaining number Your remaining credits after this request (only included when credits are charged)

Segment Object Structure

Field Type Description
text string Transcript text for this segment
start number Start time in seconds
end number End time in seconds
timestamp string Formatted timestamp (MM:SS)

Special Cases

Account replay

If this account already owns the transcript, you receive 200 OK with no credit charge:

{
"transcript": { ... },
"video": { ... },
"source": "account_replay",
"creditsCharged": 0,
"message": "You previously requested this video (no charge)"
}

A global cache hit is different: the transcript already exists on Transcript Bunny, but this account has never requested it. That still costs 1 credit and returns source: "global_cache".

Error Handling

Learn about error codes and how to handle them.

Error Response Format

When an error occurs, the API returns an appropriate HTTP status code and error details:

{
"error": "Insufficient credits",
"remaining": 0,
"upgrade": "https://transcriptbunny.com/pricing"
}

Common Error Codes

401 Unauthorized

Invalid or missing API key.

{
"error": "Missing or invalid Authorization header",
"docs": "https://transcriptbunny.com/docs"
}

Or: { "error": "Invalid API key" }

400 Bad Request

Invalid YouTube URL or missing parameters.

{
"error": "Invalid YouTube URL",
"message": "Please provide a valid YouTube video URL"
}

Or validation error: { "success": false, "error": { "issues": [...] } }

402 Payment Required

Insufficient credits to process the request.

{
"error": "Insufficient credits",
"remaining": 0,
"upgrade": "https://transcriptbunny.com/pricing"
}

404 Not Found

Video not found or transcript not available.

{ "error": "Transcript not found" }

Or: { "error": "Transcript not available", "message": "...", "creditsCharged": 0 }

429 Too Many Requests

Rate limit exceeded.

{
"error": "Rate limit exceeded",
"limit": 50,
"window": "60 seconds",
"retryAfter": 60,
"upgrade": "https://transcriptbunny.com/billing"
}

500 Internal Server Error

Server error processing your request.

{ "error": "Internal server error" }

Best Practices

  • Always check the HTTP status code first
  • Implement exponential backoff for rate limit errors
  • Log error responses for debugging
  • Check credits before making requests
  • Handle network errors gracefully

Rate Limits

Understanding API rate limits and best practices.

Rate Limit Rules

To ensure fair usage and system stability, we implement per-minute rate limits that vary by plan:

Free

5
requests per minute

Starter

50
requests per minute

Pro

100
requests per minute

Business

200
requests per minute

Credit Limits

Rate limits are separate from your credit allocation. Even with available credits, you must respect rate limits.

Response Headers

Successful API responses include rate limit information in the headers:

X-RateLimit-Limit: 50
X-RateLimit-Remaining: 48
X-RateLimit-Reset: 1609459200000

Note: Values shown are for Starter plan. Limits vary by plan. Headers are included on successful responses (200 OK). Rate limit errors (429) return error details in the JSON response body instead.

Header Descriptions

Header Description
X-RateLimit-Limit Maximum requests allowed in current window
X-RateLimit-Remaining Requests remaining in current window
X-RateLimit-Reset Unix timestamp in milliseconds when the rate limit resets

Handling Rate Limits

Example code for handling rate limits with exponential backoff:

async function fetchWithRetry(url, options, maxRetries = 3) {
for (let i = 0; i < maxRetries; i++) {
const response = await fetch(url, options);
if (response.status === 429) {
// Rate limit info is in response body
const error = await response.json();
const retryAfter = error.retryAfter || 60; // seconds until window resets
console.log(`Rate limited. Waiting ${retryAfter} seconds...`);
await new Promise(resolve => setTimeout(resolve, retryAfter * 1000));
continue;
}
return response;
}
throw new Error('Max retries exceeded');
}

Note: Rate limit errors return a 429 status with error details in the JSON response body, including retryAfter (seconds until the rate limit window resets).

Automation & Integration Tools

Use Transcript Bunny with popular automation platforms.

No-Code Integrations

Call the Transcript Bunny REST API from HTTP modules in Zapier, Make, n8n, or Pipedream. There is no native Zapier/Make app; you send POST /api/v1/transcribe with a Bearer token.

Zapier

Integrate with 5000+ apps using Zapier's Webhooks module.

Quick Setup:

  1. 1. Create a new Zap in Zapier
  2. 2. Choose "Webhooks by Zapier" as action
  3. 3. Select "POST" method
  4. 4. URL: https://transcriptbunny.com/api/v1/transcribe
  5. 5. Add header: Authorization: Bearer YOUR_API_KEY
  6. 6. Body: {"videoUrl": "YOUR_VIDEO_URL"}

Make (Integromat)

Build advanced automations with Make's visual builder.

Quick Setup:

  1. 1. Create a new scenario in Make
  2. 2. Add "HTTP" module
  3. 3. Choose "Make a request"
  4. 4. Method: POST
  5. 5. URL: https://transcriptbunny.com/api/v1/transcribe
  6. 6. Headers: Authorization with Bearer token
  7. 7. Body: JSON with video URL

n8n

Self-hosted workflow automation with full API control.

Quick Setup:

  1. 1. Create new workflow in n8n
  2. 2. Add "HTTP Request" node
  3. 3. Method: POST
  4. 4. URL: https://transcriptbunny.com/api/v1/transcribe
  5. 5. Authentication: Header Auth
  6. 6. Header Name: Authorization
  7. 7. Header Value: Bearer YOUR_API_KEY

Pipedream

Low-code integration platform with built-in triggers.

Quick Setup:

  1. 1. Create new workflow in Pipedream
  2. 2. Add HTTP request step
  3. 3. Configure POST request
  4. 4. Add Authorization header
  5. 5. Use Node.js code for advanced parsing

Example Workflows

Content Creation Workflow

Trigger: New video uploaded to YouTube → Get transcript → Generate summary with ChatGPT → Create blog post draft → Save to Notion

Educational Workflow

Trigger: New video in playlist → Get transcript → Extract key concepts → Create flashcards → Add to Anki deck

Research Workflow

Trigger: Manual trigger with URL → Get transcript → Analyze with AI → Extract citations → Save to Zotero

MCP (Model Context Protocol)

Connect AI assistants like Claude and Cursor directly to Transcript Bunny to fetch YouTube transcripts.

What is MCP?

The Model Context Protocol (MCP) is an open standard that allows AI assistants to connect to external tools and data sources. With our MCP server, you can ask Claude or other AI agents to fetch YouTube transcripts directly in your conversations.

MCP Endpoint

https://transcriptbunny.com/mcp

Requirements

  • A Transcript Bunny account on any plan, including Free (5 requests/minute, drawn from your monthly credits)
  • MCP Client: ChatGPT, Claude, Cursor IDE, or any MCP-compatible client
  • No API key needed for AI connectors - you sign in with your account via OAuth. API keys remain available for scripts and CI.

Connect in One Step (OAuth)

The easiest way to connect: paste our MCP URL into your AI app and sign in. No API keys to create, copy, or rotate.

1
Add the connector in your AI app

In ChatGPT go to Settings → Connectors → Add custom connector. In Claude go to Settings → Connectors → Add custom connector.

2
Paste the MCP URL
https://transcriptbunny.com/mcp
3
Sign in and allow access

Your browser opens to Transcript Bunny. Sign in, review the permissions, and click Allow access. That's it - your AI assistant can now fetch transcripts on your behalf.

OAuth uses short-lived tokens scoped to your account. Transcript fetches made by your AI apps use your plan's credits, exactly like API key usage. You can disconnect anytime from your AI app's connector settings.

Available Tools

Our MCP server provides two tools for fetching YouTube transcripts.

transcribe

Fetch a single transcript

Fetches the transcript for a single YouTube video. Costs 1 credit the first time this account requests the video. Replays of a transcript this account already owns are free. A transcript stored for another account still costs 1 credit.

Parameters

Name Type Description
videoId string YouTube video ID (e.g., dQw4w9WgXcQ)
withTimestamps boolean Default true. Set false for plain text without [mm:ss] prefixes.

Example Prompt

"Get the transcript for this YouTube video: https://youtube.com/watch?v=dQw4w9WgXcQ"

batch_transcribe

Fetch multiple transcripts

Fetches transcripts for multiple YouTube videos in one call (max 10). Each video costs 1 credit the first time this account requests it. Account replays are free. A transcript stored for another account still costs 1 credit.

Parameters

Name Type Description
videos array Array of objects with videoId or videoUrl

Example Prompt

"Get the transcripts for these YouTube videos: https://youtube.com/watch?v=abc123 and https://youtube.com/watch?v=xyz789"

Claude Desktop Setup

Connect Transcript Bunny to Claude Desktop for seamless transcript fetching.

Important

Claude Desktop requires remote MCP servers to be added via the Settings UI, not the config file. The config file only supports local servers.

Setup Steps

  1. 1
    Open Claude Desktop Settings

    Click on your profile icon → Settings → Connectors

  2. 2
    Add Integration

    Click "Add Integration" or "Add Connector"

  3. 3
    Enter the Integration URL
    https://transcriptbunny.com/mcp
  4. 4
    Authenticate

    Your browser opens to Transcript Bunny - sign in and click Allow access. No API key needed. (If your client only supports header-based auth, you can still use an API key from the API Keys page as a Bearer token.)

  5. 5
    Start Using

    Start a new conversation and ask Claude to fetch a transcript

Example Prompt

"Use Transcript Bunny to get the transcript for https://youtube.com/watch?v=dQw4w9WgXcQ and summarize the key points"

Cursor IDE Setup

Use Transcript Bunny with Cursor IDE's AI assistant.

Configuration

Cursor supports remote MCP servers via HTTP. Add this to your MCP configuration:

Config File Locations

  • Project: .cursor/mcp.json in your project root
  • Global: ~/.cursor/mcp.json in your home directory
{
  "mcpServers": {
    "transcriptbunny": {
      "url": "https://transcriptbunny.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Replace YOUR_API_KEY

Get your API key from the API Keys page and replace YOUR_API_KEY in the config.

After Setup

  1. 1. Restart Cursor IDE
  2. 2. Open the AI chat (Cmd/Ctrl + L)
  3. 3. Ask the AI to fetch a transcript using Transcript Bunny

Other MCP Clients

Transcript Bunny works with any MCP-compatible client that supports Streamable HTTP transport.

Connection Details

Use these details to configure any MCP client:

Setting Value
Endpoint URL https://transcriptbunny.com/mcp
Transport Streamable HTTP
Authentication Authorization: Bearer YOUR_API_KEY

Rate Limits Apply

The same rate limits from your plan apply to MCP requests. Check the Rate Limits section in API Docs for details.

Need Help?

If you're having trouble setting up MCP with your client, check that your client supports the Streamable HTTP transport (not just stdio). For further assistance, contact our support team.