Audio to video
Your audio.
Ready for YouTube, Reels and TikTok.
Upload a podcast, an interview or a voice note. Sentarys transcribes every word and builds a video with your cover, a waveform that moves with your voice and captions you can fix word by word. Prefer pictures for every sentence? The narrated recipes turn the same audio into a full visual story.
6,000 free credits on signup. No credit card.
Captions
Captions people actually read.
Word-by-word timing, emphasis on the words that matter, and styles that match your channel. Switch one tap, see it instantly.
How it works
01
Upload the audio
MP3, M4A, WAV, AAC or OGG up to 3 hours, and a cover image if you have one.
02
Pick the format
Vertical 9:16 for Shorts, Reels and TikTok, square 1:1, or wide 16:9 for YouTube. Then a caption style.
03
Fix and export
Correct any word in the editor, export the video and download SRT or VTT captions.
What you get
- Your cover, or your title on a clean background
- A waveform that moves with the voice
- Word-timed captions in five styles
- 9:16, 1:1 and 16:9 from the same audio
- SRT and VTT files to download
- Up to 3 hours per file
What it costs
Audio to video uses 50 credits per minute of audio, 200 at least. Pro is US$10 a month with 30,000 credits, about 10 hours of audio.
Simple pricing
Start with free credits. No card needed.
30,000 credits per month
About 2.5 hours of video. 200 credits per minute of video, 20 per chat reply, exports included.
- Unlimited projects
- Clip finder with scores
- Word-level captions in every style
- Auto reframe and speaker tracking
- Zooms, cuts, emoji and sound effects
- Viral formats library
- 1080p exports, no watermark
- Edit by chat
- Cancel anytime
6,000 free credits to start, enough for 30 minutes of video. Then $10/month.
Questions about turning audio into video
Upload the audio, add a cover image if you want one, pick the format and the caption style. Sentarys transcribes the speech and renders a video with your cover, a moving waveform and captions.