SRT · VTT · Subtitle files

Convert SRT & VTT files to
perfectly timed AI audio

Upload your subtitle file, choose a voice, and get back an MP3 where every word lands exactly on its cue. No timeline editor. No manual sync.

5 free minutes · No credit card required

How it works

  1. 1

    Upload your SRT or VTT file

    Drop in any subtitle file that has timestamps — SRT, VTT, or plain text with cue timings.

  2. 2

    Edit or translate the text

    Optional — fix wording, correct names, or switch the language entirely before generating.

  3. 3

    Download your MP3

    Recastr generates each segment and assembles them so every word lands exactly on its cue.

Who uses SRT-to-audio conversion

E-learning & course creators

Update course narration without re-recording. Upload your existing SRT, fix the wording, and get new audio that stays perfectly in sync with your slides.

Screen recordings & presentations

Re-voice a Loom, demo, or slide recording. Replace a weak take or localize for an international audience — without touching the video edit.

YouTube & TikTok creators

Already have captions? Use them. Swap the voice on an existing video without touching the edit. Export the audio and drop it into your video editor.

Translation & localization

Translate your SRT into any language, then generate a foreign-language voiceover timed to the original cuts. No dubbing studio required.

Frequently asked questions

What is an SRT file, and how does it differ from VTT?
An SRT (SubRip Text) file is the most common subtitle format. It contains a numbered list of text segments, each with a start and end timestamp in HH:MM:SS,ms format. A VTT (WebVTT) file works the same way but uses a slightly different timestamp notation (HH:MM:SS.ms) and is the standard for web video players. Recastr accepts both formats.
Can I use Recastr with auto-generated YouTube captions?
Yes. Download your YouTube captions as an SRT file (YouTube Studio → Subtitles → three-dot menu → Download), then upload them to Recastr. The auto-generated timestamps are accurate enough for voiceover generation.
How does Recastr keep the audio in sync with the timestamps?
Each subtitle segment is synthesised individually using the cue timings from your file. If a segment finishes early, Recastr inserts silence to hold the gap so the next segment starts exactly when your original cue says it should. No manual adjustment needed.
What audio format does Recastr output?
Recastr exports MP3 by default — compatible with every video editor, podcast host, and LMS platform. WAV is also available for lossless quality when you need it.
What voices are available?
Recastr offers multiple AI voices with different tones and styles. You can preview voices before generating, and switch if the first pick doesn't fit your content.
What languages are supported?
Recastr can generate voiceover in any language supported by the underlying AI voice models — covering most major world languages. Use the built-in translation feature to convert your SRT to the target language before generating.

Ready to convert your subtitles to audio?

5 free minutes included · No credit card required