Chapters and show notes for your videos — in minutes, not hours.
Upload once → get chapters, show notes, transcripts, and subtitles.
Copy-paste into your favorite publishing platforms instantly.
Accurate, publish-ready for any platform — minimal editing needed.
Be the first to know when PublishFlow opens up.
Automated precision for high-output creators.
Our AI understands the nuances of human conversation, identifying scene transitions and topic shifts across any platform or media type.
Drag. Drop. Done.
Supporting all major file formats including MP4, MOV, and high-fidelity WAV.
Smart Show Notes
Engaging summaries that keep your audience clicking and watching longer.
Global Reach
Multi-language transcription and subtitle generation in 25+ languages.
Seamless Export
Direct export to social media, CMS platforms, and specialized RSS feeds.
The PublishFlow Workflow
From raw media to published content in four automated steps.
1. Upload
Drag and drop your audio or video file in any major format.
2. Process
Our AI transcribes, cleans, and structures your content automatically.
3. Review
Fine-tune your chapters, summaries, and show notes in real-time.
4. Export
Download a ZIP or copy-paste sections to publish anywhere.
Frequently asked questions
Everything you need to know about turning audio and video into publish-ready chapters, show notes, and transcripts with PublishFlow.
What does PublishFlow do?
PublishFlow turns raw audio or video into a publish-ready package: chapters with timestamps, show notes, full transcripts, and multi-language subtitles. You upload once and paste the output straight into YouTube, Spotify, Apple Podcasts, Substack, or your CMS.
How does PublishFlow generate podcast chapters?
PublishFlow transcribes your audio with Whisper-class models, then uses an LLM to detect topic shifts and segment the episode. You get YouTube-style timestamped chapters that you can edit before exporting.
What file formats are supported?
PublishFlow accepts the major podcast and video formats including MP3, MP4, MOV, WAV, M4A, and WebM. Files are uploaded directly from your browser to encrypted object storage.
How accurate are the transcripts?
Transcripts are generated using state-of-the-art speech-to-text models (large-v3-turbo class), with optional Together.ai-hosted Whisper for higher accuracy on accented audio. You can review and edit every line before exporting.
Which languages does PublishFlow support?
PublishFlow supports transcription and subtitle generation in 25+ languages, including English, Spanish, Portuguese, French, German, Italian, Dutch, Hindi, Arabic, Mandarin, Japanese, and Korean.
How much does PublishFlow cost?
PublishFlow offers a free tier with 1 included episode and paid plans for high-output creators. No credit card is required to try it, and you can cancel anytime.
Is my audio data private?
Yes. Episode audio is stored in your private bucket on encrypted object storage (Cloudflare R2), is never used to train third-party models, and is accessed only via short-lived signed URLs.
Be first in line when we open up.
We're opening PublishFlow to a small batch of creators each week. Drop your email and we'll let you know the moment it's your turn.
Be the first to know when PublishFlow opens up.