Extract existing captions or generate accurate subtitles from video and audio with AI precision.
or click to browse from device
MP4 • MOV • WEBM • MKV • MP3 • WAV • M4A • AAC
High-accuracy neural recognition
Detect & translate 50+ languages
Separate voice tracks & diarize
Precise millisecond sync
Custom styling & video burn-in
Five fluid steps from raw media to styled, multi-format subtitles.
Drop your video, audio file, or paste a video link.
Whisper AI extracts speech and detects speaker tracks.
Refine captions on the interactive waveform timeline.
Apply TikTok, YouTube, Netflix, or Neon presets.
Download in SRT, VTT, ASS, or burn into video.
| Feature | Free Tier | Pro Pass | Business |
|---|---|---|---|
| Monthly Transcription Quota | 15 Minutes | 120 Minutes | Unlimited |
| Whisper Model Accuracy | Standard Fast | High Precision Large | Custom Enterprise |
| Word-Level Timestamps & Karaoke | ✕ | ✓ Included | ✓ Included |
| Multi-Language AI Translation | ✕ | ✓ 50+ Languages | ✓ 100+ Languages |
| Export Formats (SRT, VTT, ASS, CSV) | SRT Only | All Formats | All + REST API |
Get unlimited transcription minutes, word-level karaoke captions, multilingual AI translation, and all professional export formats.