API-first · Audio & Video
$5 in free credits · No credit card required

Turn audio & video intoReusableContent.

Transcription, clips, blogs & captions — API-first for developers & creators.

>get-api-key>read-the-docs→
POST/v1/transcribe
POST/v1/chapters
POST/v1/summaries
POST/v1/workflows/podcast-to-blog
POST/v1/captions
GET/v1/jobs/{id}
Simple to integrate
$ curl https://api.repurposeapi.com/v1/transcribe \
  -H "Authorization: Bearer $API_KEY" \
  -F "file=@podcast.mp3"
Core API Capabilities

What You Can Build

AI Transcription
Accurate transcription powered by Whisper v3. Supports multiple languages and formats.
Blog Generation
Transform transcripts into well-structured, engaging blog posts with proper formatting.
Chapter Breakdown
Automatically detect key topics and create organised chapter structures.
Smart Summaries
Generate multiple summary lengths for different use cases and platforms.
Powered by industry-leading AI
OpenAI
GPT-4 Processing
Whisper v3
AI Transcription
Supabase
Authentication
SignalVault
AI audit & trust layer
Built with RepurposeAPI

Who Uses It

Podcast Platforms
Auto-generate show notes, chapters, and transcripts for every episode.
See how →
Content Marketing
Turn client interviews into blog posts, case studies, and social content.
See how →
EdTech Platforms
Add searchable transcripts and summaries to course videos for better learning.
See how →
Social Schedulers
Generate platform-specific captions and clips for every social network.
See how →

Building something cool? Let us know — we'd love to feature you.

FAQ

Frequently Asked Questions

How does it work?
Upload your audio or video file via our API, and we'll process it using AI (Whisper for transcription, GPT-4 for content generation). You'll get back transcripts, chapters, summaries, blog posts, and more — all structured and ready to use.
What formats do you support?
We support MP3, MP4, WAV, M4A, and FLAC files up to 50MB. Works with podcasts, interviews, webinars, YouTube videos, and any audio content you want to repurpose.
Is it really free?
Yes. Every account starts with $5 in credits — roughly 400 minutes of transcription or 100+ workflow runs. No credit card required. After that you pay published per-endpoint rates, or commit monthly for bundled credits at a discount.
How accurate is the transcription?
We use OpenAI's Whisper model, which typically achieves 95%+ accuracy for clear audio. Accuracy depends on audio quality, accents, and background noise. You can review and edit transcripts before generating other content.
Can I use this commercially?
Absolutely! All plans (including free) allow commercial use. You own all the generated content — transcripts, blogs, captions — and can publish, sell, or use them however you like.
How long does processing take?
Transcription takes about 1.5–2× the audio length (30-min podcast ≈ 45–60 min). AI tasks like summaries and blogs add 1–3 minutes each. Results available via polling or webhooks (coming soon).

More questions? Check our full documentation or contact support.

Start repurposing. $5 in free credits, no credit card.

>get-api-key→