Seply

Seply separates multi-speaker recordings into individual, time-aligned WAV tracks. Upload a podcast, interview, meeting, panel, or video file, let the service detect speakers or provide an expected count, then preview each resulting voice and download the tracks needed for editing. Standard separation handles ordinary conversations, while Advanced Overlap is designed for interruptions and simultaneous speech. The same workspace also provides speech-to-text with speaker diarization. Transcripts retain timing, detected voice labels, overlap context, and links back to the audio. Users can filter, rename, or reassign speakers, correct wording beside the recording, follow playback by timestamp, and export revised text as TXT, SRT, VTT, or JSON. Audio and video uploads can be up to 1 GB, and the service supports more than 30 languages. Seply is useful for podcast editors, interview producers, meeting reviewers, transcription workflows, and video teams preparing subtitles. Processing is private, with completed media and results available to the signed-in account for 30 days. The credit-based workflow displays an estimate before processing and supports both subscription plans and one-time credit packs.