A subtitle generator turns speech into timed caption lines and saves them as an SRT file that video players and editors can load. Upload audio or a video, let Whisper recognize the speech, correct the text and timestamps, and download SRT, TXT or JSON. The tool creates a separate subtitle file; it does not burn captions into your original video.
See real examples
Explore the examples ↗Practical use cases
How do I get SRT subtitles for a video without changing the video?
Upload the video in Extract text, choose the spoken language and start recognition. Correct the lines and times, save, and download SRT. Add the file in your editor or video platform; the original video is never re-encoded.
Best for clear speech under 10 minutes. The tool reads the soundtrack only and does not translate or label speakers.
Specs and free limits
| Input | MP3, WAV, M4A, AAC, FLAC, OGG; MP4, MOV, WebM or MKV with sound (soundtrack only) |
|---|---|
| Maximum size | 100 MB per file |
| Maximum length | 10 minutes per file |
| Output | SRT, TXT or JSON |
| Frame and resolution | No video is rendered |
| Recognition languages | English, Chinese, Japanese, Korean, Spanish, French, German or automatic detection |
| Watermark | None |
| Sign-up | Not required |
| File retention | Deleted after 24 hours |
| Price | Free; shared queue and hourly usage limit |
Supported formats
Upload MP3, WAV, M4A, AAC, FLAC, OGG, MP4, MOV, WebM or MKV. Download SRT (numbered cues with start and end times), TXT or JSON.
How it works
1. Open Extract text and upload
Choose a local audio file or a video with sound. For a video, the soundtrack is extracted on the server; text already printed in the frames is not read.
2. Choose the spoken language
Select English, Chinese, Japanese, Korean, Spanish, French or German, or automatic detection, and start recognition.
3. Correct lines and timestamps
Fix names, punctuation and start and end times in the result editor, then save. Times must stay in order and inside the recording.
4. Download the SRT file
Download SRT and load it in your video editor, your player or a video platform that accepts SRT uploads. TXT and JSON are also available.
Is it right for you?
Good fit
- Creating an SRT file for a talk, lesson, interview or short video
- Getting a first draft of captions to correct before upload
- Videos that need a separate subtitle file rather than a re-encoded video
Not a good fit
- Burning subtitles onto your original video footage
- Recordings longer than 10 minutes or larger than 100 MB
- Translated subtitles, speaker labels or VTT and ASS formats
Limits and privacy
Audio and video up to 100 MB and 10 minutes; up to 1,000 lines when editing a transcript. Free without sign-up; queue and hourly usage limits apply. Results expire after 24 hours.
What to check before sharing
Recognition can miss words or mishear names, especially with music, noise or overlapping speakers. Timestamps are model estimates. The tool does not translate subtitles, label speakers, export VTT or ASS, or burn captions into the original video. To show captions inside a new video, use the MP3 to video converter, which renders captions over a new background instead of your original footage.
Common questions
What is an SRT file?
SRT is a plain-text subtitle format. Each cue has a number, a start and end time such as 00:00:01,250 --> 00:00:03,900, and the caption text. Most video editors and players can import it.
Can I generate subtitles from a YouTube or TikTok link?
No. Upload a local file. Platform links and in-browser recording are not supported.
Will the subtitles be burned into my video?
No. You receive a separate SRT file; your original video is not modified or re-encoded. Load the SRT in an editor or player to display it.
Can it translate subtitles into another language?
No. Subtitles are produced in the spoken language. Translate the SRT with a separate tool if needed.
Which languages are supported?
English, Chinese, Japanese, Korean, Spanish, French and German, plus automatic detection. Accuracy varies with recording quality.
Compare free audio to video tools ↗
Product facts
AI Free Audio to Video · audiosubvideo.com
- Price and account
- Free to use without payment or sign-up; 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.
- Downloads
- MP4 for videos; TXT, JSON and SRT for timed transcripts; TXT and JSON for image OCR.
- Who can access results
- The originating browser session and signed-in site administrators. Uploaded content is not a public case study.
- Audio and video limits
- 100 MB · 10 min
- Completed file retention
- 24 hours