Supported file formats, sizes and sources

Formats, device upload limits, Paste link limits (up to 2 GB) and supported platforms for all VocaLingo tools.

Written By Umakhan Magomedov

Last updated 3 days ago

This page lists file formats, size limits and supported link sources for all VocaLingo tools. Limits depend on how you add the file: manual upload from your device vs Paste link (server download).

Audio files

Used in: Translate Audio, Speech to Text, Text Analysis

Formats

MP3, M4A, WAV, OGG, FLAC, AAC, OPUS, WebM

Video files

Also accepted in these tools — the audio track is extracted automatically

Device upload

100 MB (audio files from gallery or Share)

Paste link

2 GB — downloaded on the server (YouTube, Instagram, TikTok or direct URL). See Importing audio from a link.

Video files

Used in: Translate Video, Video to Text, Add Captions

Formats

MP4, MOV, AVI, MKV, WebM, M4V

Video to Text — device upload

Large source files supported. The app compresses video before upload when needed.

Translate Video — device upload

Large source files supported. Video is compressed to about 100 MB before upload.

Add Captions — device upload

Up to 50 MB and 5 minutes after compression (Mirage API limit).

Paste link (video tools)

2 GB — server download for YouTube, Instagram, TikTok or a direct video URL.

Paste link is available in Translate Audio, Speech to Text, Text Analysis, Translate Video, Video to Text and Add Captions.

Source

Audio tools

Video tools

YouTube

✅

✅

Instagram

✅

✅

TikTok

✅

✅

Direct audio URL (.mp3, .m4a…)

✅

❌

Direct video URL (.mp4, .mov…)

✅ (audio extracted)

✅

ℹ️ Private or age-restricted videos may not be downloadable via link. Upload the file directly in that case.

Files in AI Chat

You can attach files directly to a chat message:

Max files per message

5

Max size per file

50 MB (videos are compressed before upload)

Knowledge base upload

Up to 1 GB per file

Frequently asked questions