Seply

Seply uploads a mixed recording (audio or video) and uses AI to detect speakers, either automatically or using a number the user enters, then produces a separate time-aligned WAV track for each speaker that can be previewed and downloaded. The page also offers an Advanced Overlap mode for overlapping speech, a separate Speech to Text tool with speaker labels and timestamps, guides for common tasks, and credit-based pricing with a free trial of 20 credits for new accounts. Results are stored privately for 30 days.

Key features

• Individual speaker tracks, one independent audio track per detected speaker
• Time-aligned WAV output starting at the same point as the original recording
• Automatic speaker detection or manual entry of expected speaker count
• Audio upload support for WAV, MP3, M4A, AAC, FLAC; video upload support for MP4 and MOV (AAC or PCM audio)
• Uploads up to 1 GB
• Preview each speaker track and download only the needed WAV files
• Advanced Overlap mode for overlapping or simultaneous speech (requires a successful purchase)
• Separate Speech to Text tool with speaker labels and timestamps
• Private processing with 30-day protected result access
• Credit-based pricing with estimated cost shown before processing

Best suited for

• Podcast hosts and guests who need separate editable tracks
• Interviewers and guests in interview recordings
• Meeting, panel, and multi-speaker conversation editing
• Teams that want to split voices from video audio for editing in another editor
• Users who need transcripts with speaker labels (via Speech to Text)

Pricing

Free trial: 20 one-time credits valid for 30 days, no card required. Paid plans: Starter $12/month (200 credits), Creator $29/month (600 credits), Studio $65/month (1,500 credits), with annual billing options and one-time credit packs (Basic 200 credits $16, Standard 600 credits $39, Pro 1500 credits $89). Prices are in USD.