Today's usage (per tool)

Transcribe

Converts speech in an audio file to text. Supports WAV, MP3, M4A, OGG, FLAC — up to 10MB. Long files are processed in chunks, so it works for anything from a voice memo to a full interview.

English (US) English (UK) Spanish French German Italian Portuguese Russian Japanese Korean Chinese (Mandarin) Arabic Hindi Turkish Polish Dutch

Convert

Changes an audio file's format and bitrate. Supports MP3, WAV, OGG, M4A, FLAC — up to 10MB.

Merge — combine 2 or more clips, in order

Stitches multiple clips into one file with a configurable silence gap between them. Up to 10MB per file.

Tap "Add files" as many times as you need — each pick adds to the list below rather than replacing it. Max 10MB per file.

+ Add files

Cutter

Trim a clip to a start/end range, or split it into two files at a chosen point. Up to 10MB.

Denoise

Reduces background hiss/hum using spectral noise reduction. Works best on speech with fairly steady background noise (fans, room tone) — won't remove sudden noises like claps or barks. Up to 10MB. Output is mono.

Strength: 0.5

Voice Changer

Applies an effect to a voice clip — Pitch Shift preserves the original speaking speed while changing pitch; Chipmunk/Deep Voice intentionally change both pitch and speed for a character-voice effect. Up to 10MB.

Pitch Shift Robot Echo Chipmunk Deep Voice

Video to Audio

Extracts the audio track from a video file. Supports MP4, AVI, MOV, MKV, WEBM — up to 50MB (larger than the other tools, since video files are naturally bigger). Files over the limit, or corrupted/incomplete uploads, will fail with an error rather than a silent hang.

Music generator — Pro only

Generate real instrumental or vocal tracks from a text description — for videos, projects, anything. Upgrade to Pro to unlock this.