AudiotoVideoAI
English
Free to useStart creating
Free media tools

Translate speech to English subtitles

Translate uploaded speech to English text, SRT or VTT using the installed multilingual Whisper model. Check translation and timing before publishing.

Multiple files keep the order shown here. Re-select to change their order.

    Experimental: English is the only target language. Choose the source speech language for better results. The small model can mistranslate clear speech; review every cue. No dubbed audio track is generated.

    The end is capped at the actual file duration.

    Preview and result

    Your result will appear here.

    Recent tool results

    Last reviewed:

    Supported inputs and outputs

    Input
    MP3, WAV, M4A, AAC, OGG or FLAC; a local video with an audio track also works.
    Output
    English TXT, SRT or VTT; experimental translation, no dubbing.

    How to use this tool

    1. Sign in with Google and choose your own source or enter text.
    2. Choose the time range and audio settings, export, then listen to the beginning and end.
    3. Review the actual result and download it before leaving.

    Common questions

    Can I translate into any language or generate dubbing?

    No. This experimental tool uses the installed Whisper model to translate speech into English text, SRT or VTT only. It can mistranslate names and whole sentences. Review it against the original; no translated voice is generated.

    Is it free, and do I need an account?

    Yes, it is free with Google sign-in, with no payment or subscription. Server processing shares the account’s hourly and queue limits.

    Where are my files stored?

    Browser-only tools keep their work on your device. Uploaded server jobs are private by default, accessible to the owner and site administrators, and retained for 14 days. Download results you want to keep.

    Related media tools

    Audio cutterAudio converter · MP3, WAV, M4AAudio cleanup and normalizationAudio joiner

    Limits and processing

    Free with Google sign-in. Uploads total up to 100 MB; audio and video up to 10 minutes. Each image is limited to 5 MB and 20 megapixels, all images together to 40 megapixels; output images to 4 megapixels. GIF and reverse exports are limited to 30 seconds and 640 pixels per side; reverse uses 15 fps to limit memory use. Join up to six media files or combine up to nine images. Server results are private and kept for 14 days.

    Shared account limits: 10 tasks per hour, with at most 2 tasks queued or processing at once. UTF-8 SRT/VTT files up to 200 KB are supported.

    Basic noise reduction, stabilization and sharpening depend on the source. They do not reconstruct missing details or isolate vocals. Files are processed with installed open-source components; no paid model API is used. Browser recording and speech availability depend on your device. Upload only material you are allowed to use.

    There are no anonymous public file links or platform-video downloads. Sharing is optional, revocable, requires viewer sign-in and expires with the file. For automatic captions and transcription, use the existing tools below.

    Edit subtitlesExtract textMusic videoAll media tools