Models tagged "audio-to-audio"

🤖 Model 🎥

zsxkib/hibiki

Translate spoken French to English while preserving the speaker’s voice, outputting English speech audio. Accept an audi...

🎥 • speech-translation • audio-to-audio • video-to-audio • 17 runs

🤖 Model 🔊

cuuupid/seamless_expressive

Translate speech to another language while preserving the speaker’s voice, style, pronunciation, and tone. Accepts spoke...

🔊 • speech-translation • audio-to-audio • 807 runs

🤖 Model 🔊

ardianfe/demucs-prod

Separate music into stems from an input audio file using Demucs. Remove vocals to generate an instrumental/no‑vocals tra...

🔊 • music-source-separation • audio-to-audio • 55.4K runs

🤖 Model 🔊

ardianfe/demucs-prod2

Separate songs into stems from an audio input. Outputs isolated tracks for vocals, drums, bass, guitar, piano, other, an...

🔊 • music-source-separation • audio-to-audio • 1.7K runs

🤖 Model 🔊

pconihout/mbd-synthia

Generate music from a text prompt. Control the duration in seconds and optionally continue from an existing audio clip t...

🔊 • music-generation • audio-to-audio • 89 runs

🤖 Model 🔊

naclonts/musicgen-experiment-2

Generate music from a text prompt. Optionally condition on an input audio clip to mimic its melody or continue the clip...

🔊 • music-generation • audio-to-audio • 23 runs

🤖 Model 🔊

soykertje/spleeter

Separate music audio into two stems from a single input track, outputting isolated vocals and accompaniment. Accepts an...

🔊 • music-source-separation • audio-to-audio • 792.9K runs

🤖 Model 🔊

myaiteam2/song-cutter-upper

Split an audio file into fixed-length segments. Provide an audio file and a maximum segment length in seconds; returns a...

🔊 • audio-to-audio • audio-splitting • 104 runs

🤖 Model 🔊

cjwbw/demucs

Separate music into stems for remixing, karaoke, and sampling. Takes an audio input and outputs isolated vocals, drums,...

🔊 • music-source-separation • audio-to-audio • vocals-removal • 430.9K runs

🤖 Model 🔊

myaiteam2/audio-trimmer-with-fade

Trim MP3 audio to a specified segment and optionally add a 2.5-second fade-out. Accepts an MP3 file plus start_time and...

🔊 • audio-to-audio • audio-editing • 534 runs

🤖 Model 🔊

nikitalokhmachev-ai/silero-vad

Remove silence from audio recordings. Accept an input audio file and return audio with non-speech segments removed using...

🔊 • audio-to-audio • voice-activity-detection • silence-removal • 99 runs

🤖 Model 🔊

lucataco/singing_voice_conversion

Convert singing voice recordings to the timbre of a selected professional singer. Takes a source vocal audio input and o...

🔊 • audio-to-audio • voice-cloning • singing-voice-conversion • 1.0K runs

🤖 Model 🔊

chuanenlin/illeniumgen

Generate music from a text prompt. Optionally condition on an input audio clip to continue a selected segment or mimic i...

🔊 • music-generation • audio-to-audio • 45 runs

🤖 Model 🔊

petelouise/perrey-pizzicato-samba

Generate music from a text prompt. Optionally condition on an input audio file to mimic its melody or continue the clip...

🔊 • music-generation • audio-to-audio • 11 runs

🤖 Model 🔊

stability-ai/stable-audio-2.5

Generate music and sound effects from a text prompt. Accept a text description (e.g., genre, BPM, instrumentation, mood)...

🔊 • music-generation • audio-to-audio • sound-effect-generation • 2.8K runs

🤖 Model 🔊

resemble-ai/resemble-enhance

Enhance and denoise audio recordings. Takes an audio file as input and outputs an enhanced version, with optional noise...

🔊 • audio-denoising • audio-to-audio • 199.5K runs