lingua.direct
lingua.direct AI Voice Translation

Mũtaarĩri wa Faimu ya Ũhoro kuuma Kifiji nginya Kĩace

Upload a recording or video, get a translated transcript, a subtitle file, or the translation spoken back.

Kũrĩ na kĩhumbe gĩa guthuthuria gatagatĩ ka Kifiji na Kĩace. Gũtirĩ mũgambo wa kwaria wa Kĩace, tũmĩra mwandĩko o wiki.

Audio file mode handles recordings you already have on disk: a voice memo, a recorded interview, a podcast episode, a voicemail. Upload it once and get back a clean transcript plus a translation, with optional read-aloud audio in your target language.

How it works

  1. 1

    Drop in the file

    MP3, M4A, WAV, MP4, MOV. Up to 6 hours per file.

  2. 2

    Pick the target language

    Source language is detected automatically.

  3. 3

    Read or download

    The transcript and translation appear line by line, timed to the audio. Download as .srt or .vtt for a video player, or as plain text to read and edit.

Frequently asked

What file formats work?

Common audio (MP3, M4A, WAV, OGG, Opus) and video (MP4, MOV, WEBM, MKV): with video the audio track is extracted and only that is transcribed and billed. A video without an audio track cannot be used.

Is there a length limit?

Up to 6 hours per file, and up to 1 GB. Longer than that: split the recording and upload each part.

How accurate is the transcript?

Very accurate on clear single-speaker recordings. Multi-speaker overlap, heavy accents and music in the background lower accuracy, as they do for any speech-to-text system.