Extract One Speaker from a Recording
Yi wa mai maganar farko fice daga duk wani abu - wasu sauti, kiɗa da zafi - don samun wani raƙumi na magana ɗaya mai da hankali daga wani rikodin mai nauyi.
AI model Wannan kayan aiki na tafiyar da wani nau'in AI na halitta a kan GPU, don haka yana ɗaukar lokaci mai tsawo fiye da sifofin da aka yi a hankali. Free to try; paid plans get priority on the GPU.
Yadda yake aiki
The separation engine extracts the foreground voice and pushes background talkers, music and ambience down, leaving the target speaker as the clear centre of the recording.
What it's good for
- Pulling one host from a noisy room
- Focusing a presenter over a crowd
- Isolating dialogue from ambience
- Prepping a clean voice for cloning
Details
- Mai Gudanarwa
- Mel-Band RoFormer
- Formats
- MP3, WAV, M4A, FLAC, OGG, AAC
- Price
- Free to try
Tambayoyi da ake yi da yawa
Denoising removes non-speech noise but leaves other voices and music. Target-speaker extraction also removes competing voices and music, keeping only the main speaker.
Not today — it extracts the dominant foreground voice automatically. Reference-guided extraction is planned for a future update.
An rage su sosai. Wani sauti na baya mai ƙarfi kamar na manufa shi ne mafi tsanani kuma zai iya barin wasu alamun alamun.
An yi amfani da wannan fasahar wajen yin amfani da sauti da kuma sauti mai kyau a cikin waƙoƙin da aka yi amfani da su a cikin fina-finai da kuma fina-finai.
It produces a focused single-voice track that works well as cloning input, though a short, naturally clean recording will always beat a heavily processed extraction.
Na'am, kiɗa da yanayi an sanya su ƙasa tare da masu magana masu gasa, don haka mai maganar manufa an bar shi a matsayin farfajiyar bayyanar na rikodin.
%s: Mafi yawan waƙoƙin suna ƙaruwa cikin minti ɗaya, tare da lokacin aiwatarwa yana danganta da tsawon waƙoƙin da aka yi wa rajista fiye da yadda aka yi da kyar a cikin bango.