Edit subtitles keeps your uploaded video footage and adds editable, timed captions. Whisper small creates a draft on the website server. Review each line, choose one of eight caption styles, and export an MP4 with the subtitles visible in the picture or download SRT separately.
See a real export
Punchy portrait captions
Pulse animation, four-word groups and a bright highlight over the original footage. · 66.0 s
Independent original human narration is combined with licensed film excerpts. The movie dialogue is not transcribed. Framing, captions and the declared audio/cut settings are applied. No synthetic voice or replacement performance is generated.
Watch the full example and see every setting ↗ · CC-BY-4.0
Source credits & licenses
(c) copyright 2008, Blender Foundation / www.bigbuckbunny.org
Original source · CC-BY-3.0
Mark Twain | Read by John Greenman / LibriVox
Original source · LibriVox-Public-Domain
See real examples
- Punchy portrait captions
- Cinematic neon subtitles
- Marker highlights on real footage
- Editorial reading: a quiet portrait
- Minimal landscape captions
- Typewriter narration in a square frame
- Outline captions: strong contrast
- Mono captions for a documentary look
- Bold portrait: two words at a time
- Wide neon story with a B-roll moment
- Mint marker: square social captions
- Editorial wide frame with clean audio
- Minimal portrait with image B-roll
- Typewriter: upper-case landscape
- Electric outline: square story
- Mono portrait with subtle music
- Caption-led cut: remove a sample pause
- A tighter opening: trimmed landscape
- A clean ending: square editorial cut
- Layered portrait: captions, music and B-roll
Practical use cases
How do I add word highlights to a talking video?
Open Edit subtitles, upload your video and select its spoken language. Review the draft, choose pulse, marker or neon, adjust the word-group length and position, and render the MP4.
Recognition and timing may need correction. The final video keeps the source footage; this is not automatic highlight selection.
How do I combine captions with B-roll and music?
Review the transcript, upload one B-roll image or video, set its start and end, and add a music track at a low volume. Use a short title or center zoom if suitable, then inspect the rendered transitions.
Only one scheduled B-roll asset and one music track are supported. Media is supplied by you, not automatically sourced or generated.
Specs and free limits
| Input | MP4, MOV, WebM or MKV with sound |
|---|---|
| Maximum size | 100 MB per file |
| Maximum length | 10 minutes per file |
| Caption styles | Pulse, marker, neon, editorial, minimal, typewriter, outline and mono |
| Output | MP4 (H.264 video, AAC audio) or SRT captions |
| Frame and resolution | 9:16, 16:9 or 1:1 at 720p or 1080p |
| Watermark | None |
| Sign-up | Google sign-in required |
| File retention | Deleted after 24 hours |
| Price | Free; shared queue and hourly usage limit |
Supported formats
Upload MP4, MOV, WebM or MKV with an audio track. Export H.264/AAC MP4 in 9:16, 16:9 or 1:1 at 720p or 1080p, or download SRT captions.
How it works
1. Upload and transcribe your video
Sign in with Google and upload a local video with sound, up to 100 MB and 10 minutes. Select the spoken language or automatic detection. Recognition runs on the website server; wait for the editable transcript.
2. Review words, timing and presentation
Play the source and correct each caption and its start/end times. Choose pulse, marker, neon, editorial, minimal, typewriter, outline or mono styling. Adjust word groups, size, position, colors and frame shape. Recheck word timing after replacing a phrase: edited words use estimated subdivisions.
3. Combine cuts, zoom and media
Trim the beginning or end, exclude caption rows, optionally remove quiet intervals or enable rhythmic center zoom. Add a short opening title, one scheduled image or video B-roll asset, and a music track. Listen to the original audio and music together.
4. Check and download the result
Render the video and check the beginning, edited sections and ending with sound. Download MP4 for burned-in captions or SRT for separate subtitles. Your private source, draft and output expire after 24 hours.
Is it right for you?
Good fit
- Adding readable, animated captions to your own short video
- Correcting caption text and timing before MP4 or SRT export
- Combining a short title, simple cuts, center zoom, B-roll and background music
Not a good fit
- Automatic viral-highlight selection or social publishing
- Face tracking, multicam or a multitrack timeline
- Recordings longer than 10 minutes or larger than 100 MB
Limits and privacy
Free with Google sign-in; shared queue and hourly generation limits apply. A source video must be no larger than 100 MB and no longer than 10 minutes. Music accepts audio or a video soundtrack; a B-roll image must be JPG, PNG or WebP up to 5 MB, or a supported video within the upload limit. Private project files are accessible to the account owner and authenticated site administrators and are removed after 24 hours.
What to check before sharing
Speech recognition and word timestamps are estimates. Review names, singing, overlapping voices and manually replaced words. Quiet-interval removal can cut meaningful pauses, so inspect the output. Zoom is a rhythmic center crop, not face tracking. Noise reduction is optional filtering, not vocal separation. This is a single-video workflow with one scheduled B-roll asset and one music track; it does not automatically select highlights, generate B-roll, translate, clone voices or publish to social platforms.
Common questions
Can I keep my original video and add subtitles?
Yes. Use Edit subtitles for captions over your original footage. Create video and animated text tools instead build new visuals from a soundtrack.
Can I download SRT without rendering a video?
Yes. After recognition and review, download the timed caption draft as SRT. MP4 export renders captions into the picture.
Can I change incorrectly recognized words?
Yes. Edit captions and line times before exporting. When a phrase is replaced, word timing inside it is estimated, so listen and check the exported result.
Does zoom follow a face?
No. The optional zoom is a rhythmic crop around the center of the frame. Check that important content remains visible.
Can I inspect real subtitle examples before signing in?
Yes. The public example gallery can be watched without signing in. Sources, caption files, licenses and settings are disclosed. Creating your own project requires Google sign-in.
Compare free audio to video tools ↗
Product facts
AI Free Audio to Video · audiosubvideo.com
- Price and account
- Free to use with Google sign-in and no payment; shared queue and hourly usage limits apply.
- Speech and image recognition
- Whisper small for speech and Tesseract for images on the production server. No speaker identification, transcript translation or vocal separation.
- Edit subtitles
- Keep original footage, review Whisper captions and choose eight styles. Combine simple cuts, quiet-interval removal, center zoom, one B-roll asset and a music track; export MP4 or SRT.
- Map video
- Free vector maps with 11 themes and seven animation modes; coordinates or GPX / GeoJSON input; 8–90 second MP4. Google imagery, search and road planning require optional configuration.
- Downloads
- MP4 for videos; TXT, JSON and SRT for timed transcripts; TXT and JSON for image OCR.
- Who can access results
- The signed-in account owner and authenticated site administrators. Uploaded content is not a public case study.
- Audio and video limits
- 100 MB · 10 min
- Completed file retention
- 24 hours