Comments
>log in to commentHello DevHunt community! We built Seply to let you upload an audio or video file and get separate, time‑aligned WAV tracks for each detected speaker—preview them and download only what you need, all in the browser with no installation. Let us know what you think 😊
- Automatic speaker detection
- Individual time‑aligned WAV tracks per speaker
- Speech‑to‑text transcription with speaker labels
- Browser‑based, no installation required
- 30 free credits for new users
- Supports audio and video files
Seply AI Speaker Split separates multi-speaker audio or video into individual, time-aligned WAV tracks using AI.
- for
- Podcasters, interview producers, meeting recorders, and video editors needing separate speaker audio.
- pricing
- freemium · free trial
Key features
- Individual speaker tracks — Creates a separate WAV file for each detected speaker.
- Time-aligned output — All tracks start at the same point, staying in sync with the original recording.
- Automatic speaker detection — AI detects speakers automatically, with optional manual count.
- Audio & video support — Accepts WAV, MP3, M4A, AAC, FLAC, and video formats like MP4 and MOV up to 1 GB.
- Preview and download — Listen to each isolated voice before exporting the desired tracks.
- Secure private processing — Jobs are processed privately with 30-day protected result access.
Use cases
- Split podcast host and guest audio into separate tracks for independent editing.
- Isolate interviewer's and interviewee's voices for clean post-production.
- Generate speaker-labeled transcripts for searchable meeting notes.
- Extract a single speaker’s voice from a multi-person recording.
Seply AI Speaker Split pricing
- Free Trial$020 credits once · 2 minutes of speaker separation · 60 minutes of transcription
- Starter$12/month200 credits monthly · 20 minutes of speaker separation · 600 minutes of transcription
- Creator$29/month600 credits monthly · 60 minutes of speaker separation · 1800 minutes of transcription
- Studio$65/month1,500 credits monthly · 150 minutes of speaker separation · 4500 minutes of transcription
- Basic$16200 credits one-time · 20 minutes of speaker separation · 600 minutes of transcription
Seply AI Speaker Split vs alternatives
 Seply AI Speaker Split |  Otter.ai |  OpenAI Whisper |  Whisper.cpp |  Piper TTS | |
|---|---|---|---|---|---|
| Best for | AI-driven speaker separation | AI meeting transcription | Speech recognition | Local speech recognition | Text-to-speech |
| Pricing | Freemium | Subscription | Free | Free | Free |
| DevHunt upvotes | 1 | 0 | 0 | 0 | 0 |
| Launched | Oct 2026 | — | — | — | — |
- Seply AI Speaker Split vs Otter.ai: Otter.ai provides transcription and meeting notes but not separate speaker audio tracks.
- Seply AI Speaker Split vs OpenAI Whisper: OpenAI Whisper is a speech-to-text model, not a speaker-separation tool.
- Seply AI Speaker Split vs Whisper.cpp: Whisper.cpp runs speech recognition locally, lacking speaker-track output.
- Seply AI Speaker Split vs Piper TTS: Piper TTS generates synthetic speech, unrelated to separating existing audio.
Seply AI Speaker Split FAQ
Can AI separate two voices in one recording?+
Yes, Seply splits spoken conversations into separate, time-aligned WAV tracks for each detected speaker.
Can I separate overlapping speech?+
Advanced Overlap mode handles interruptions and simultaneous speech, but requires purchase and results may vary.
What file formats are supported?+
Standard supports WAV, MP3, M4A, AAC, FLAC, OGG, OPUS, WMA, Speex, MP4, AVI, MOV, MKV, WebM; Advanced Overlap adds some limits.
How do credits work?+
Standard separation costs 10 credits per started minute (minimum 10); Advanced Overlap costs 60 credits per started minute; transcription costs 1 credit per 3 minutes.
Do credits expire?+
Monthly plan credits expire 30 days after grant; one-time credit packs expire 12 months after purchase.
Summarized by DevHunt from seply.org · Oct 17, 2026. Details may change; check the official site.
