Seply

AI speaker separation that splits one recording into individual, time-aligned WAV tracks per detected speaker.

Seply introduction

Seply is an AI speaker separation tool that splits podcasts, interviews, meetings, or video audio into a separate WAV track for each detected speaker. Users can preview each voice and download the tracks they need. It supports audio and video uploads, automatic or manual speaker counts, and credit-based pricing with a free trial.

Website:: seply.org

🎼 Music & Audio Generationfreemium

Seply overview

Seply converts a single mixed recording into individual, time-aligned WAV tracks for each detected speaker. Users upload an audio or video file, let Seply detect speakers automatically or enter the expected number, then preview and download the tracks they need. The tool is designed for speech in podcasts, interviews, meetings, panels, and other multi-speaker recordings, and it distinguishes speaker separation from speaker diarization: separation produces editable audio tracks, while diarization labels who spoke when. A Standard mode handles ordinary turn-taking conversations, and an Advanced Overlap mode is designed for interruptions and simultaneous speech. Processing is described as private, with 30-day private result access. Pricing is credit-based, with a one-time free trial and monthly, annual, or one-time credit pack options.

Seply features

Individual speaker tracks: each detected speaker gets an independent audio track
Time-aligned output: every track starts at the same point as the original recording
Automatic speaker detection or manual entry of the expected speaker count
Audio and video file support
Editor-ready WAV downloads
Standard mode for ordinary turn-taking conversations
Advanced Overlap mode for interruptions and simultaneous speech
Preview each speaker track before downloading
Private processing with 30-day private result access
Credit-based pricing with an estimate shown before processing
Speech to Text tool with speaker labels and timestamps
30+ languages supported

Questions about Seply

Seply pros

Creates individual, time-aligned WAV tracks per detected speaker
Supports both audio and video uploads
Offers automatic speaker detection or manual speaker count
Advanced Overlap mode is designed for interruptions and simultaneous speech
Preview tracks before downloading
Credit estimate is shown before processing
Free trial with 20 credits and no card required
Private processing with 30-day result access

Seply limitations

Designed for speech, not for separating singers from a song
Advanced Overlap results vary with noise, echo, similar voices, and overlap; some of the other voice may remain
Advanced Overlap requires a successful purchase and is not covered by the free trial
Video workflow exports separate WAV tracks, not an edited or dubbed video
Monthly plan credits expire 30 days after they are granted
One-time credit packs expire 12 calendar months after purchase
Used credits and completed jobs are generally not refundable

Seply use cases

Splitting podcast host and guest into separate editable tracks
Separating interviewer and guest audio for interviews
Isolating individual speakers from meeting recordings
Handling panels and other multi-speaker recordings
Separating overlapping or simultaneous speech with Advanced Overlap
Keeping only one person's voice from a conversation
Extracting speaker audio from video files as WAV tracks
Preparing speaker-labeled transcripts with the Speech to Text tool

Who Seply is for

Podcast producers
Interviewers and interview editors
Video editors
Meeting and panel organizers
Audio editors working with multi-speaker recordings

Seply pricing

Free trial: 20 one-time credits valid for 30 days, no card required, covering about 2 minutes of Standard Separation or 60 minutes of transcription. Monthly plans: Starter $12/month (200 credits), Creator $29/month (600 credits), Studio $65/month (1,500 credits); annual billing saves 17%. One-time credit packs: Basic 200 credits for $16, Standard 600 credits for $39, Pro 1,500 credits for $89, valid for 12 months. Standard Separation uses 10 credits per started minute with a 10-credit minimum; Advanced Overlap uses 60 credits per started minute with a 60-credit minimum and requires a successful purchase. Speech to Text uses 1 credit per started 3 minutes. Prices are in USD.