Upload a noisy recording and get back just the voice — no hum, traffic, echo or background music. Built for podcasts, interviews, voice notes and video voiceovers.
10 credits per minute of audio · only charged when it's done
Interviews recorded in a café, voiceovers with a fan in the background, phone recordings with street noise, lectures with room echo. The model keeps the speaker's tone and removes what is around it, so the result drops straight into your editor.
Background noise, hum, wind, traffic, crowd chatter, room echo and background music — anything that isn't the spoken voice.
MP3, WAV, M4A, AAC or OGG, up to 10 MB and 10 minutes per file.
10 credits per minute of audio, charged by the second and only when the cleaned file is ready. New accounts get 18 free credits.
It keeps the voice and removes everything else, so it works as a rough vocal extractor. For music production, a dedicated stem splitter will give cleaner results.
The file is sent to our AI provider only to process it. The cleaned result is linked in My Audio so you can download it again.
18 credits on sign-up, no card. 60+ voices, 30+ languages, multi-speaker dialogue.