Seply is an AI-powered speaker separation tool for podcasts, interviews, meetings, and other multi-speaker recordings. Upload an audio or video file, automatically detect the speakers, and export each voice as an individual, time-aligned WAV track. Seply also offers speaker-labeled transcription for searchable text, subtitles, and editing workflows.
ElevenAgents by ElevenLabsScale conversations without scaling your team
Promoted
Maker
📌
Hey Product Hunt 👋
I built Seply because separating people from a recorded conversation still takes far too much time.
Speaker labels weren’t enough—I wanted the actual voices on separate, editable tracks, without losing their original timing. So Seply turns one mixed podcast, interview, meeting, or video into an individual, time-aligned WAV track for each speaker.
Real conversations are messy. People interrupt each other, rooms echo, and recordings are rarely perfect. Building Seply has meant testing against that messiness and trying to make one difficult part of audio editing feel simple.
Seply isn’t magic, but I hope it saves you from hours of manual cutting. You can try it with 30 free credits, no card required.
I’d love your honest feedback—especially from podcasters, editors, and journalists. What’s the hardest recording you’ve ever had to clean up?
Thanks for checking out Seply. It genuinely means a lot. ❤️