Models tagged "audio-to-audio"

🤖 Model 🔊

fofr/musicgen-sonic

Generate retro 16-bit Sonic the Hedgehog 2–style music from a text prompt. Optionally condition on an input audio clip t...

🔊 • music-generation • audio-to-audio • 330 runs

🤖 Model 🔊

fofr/musicgen-mario

Generate 8-bit chiptune music in the style of Super Mario Bros (1985) from a text prompt. Optionally condition on an inp...

🔊 • music-generation • audio-to-audio • chiptune • 166 runs

🤖 Model 🔊

ryan5453/demucs

Separate music into stems from an audio file. Ingests a song or mix and outputs isolated tracks for vocals, drums, bass,...

🔊 • music-source-separation • audio-to-audio • vocal-removal • 713.8K runs

🤖 Model 🔊

wynncjf/musicgen_balearic_house_finetune

Generate Balearic house music from a text prompt. Optionally condition on an input audio clip to mimic its melody or con...

🔊 • music-generation • audio-to-audio • 56 runs

🤖 Model 🔊

lclrke/musicgen-ltb

Generate music from a text prompt. Fine-tuned MusicGen model that can also condition on an input audio clip to mimic its...

🔊 • music-generation • audio-to-audio • 130 runs

🤖 Model 🔊

fofr/musicgen-kenji-kawai

Generate music from a text prompt or continue a reference audio clip. Accepts a text description and optional input audi...

🔊 • music-generation • audio-to-audio • 27 runs

🤖 Model 🔊

vidalfer/game-music-generator

Generate emotion-conditioned game music from a text prompt. Optionally condition on an input audio clip to continue a se...

🔊 • music-generation • audio-to-audio • 206 runs

🤖 Model 🔊

andreasjansson/musicgen-bacharach-vox

Generate music in the style of Burt Bacharach from a text prompt. Optionally condition on an input audio clip to mimic i...

🔊 • music-generation • audio-to-audio • 56 runs

🤖 Model 🔊

aaronbesson/m3maker

Generate music from a text prompt or continue a reference audio clip. Accepts a text description and optional input audi...

🔊 • music-generation • audio-to-audio • 667 runs

🤖 Model 🔊

fofr/musicgen-xmas

Generate Christmas-themed music from a text prompt. Create stereo holiday tracks (carols, jingles, festive orchestration...

🔊 • music-generation • audio-to-audio • christmas-music • 185 runs

🤖 Model 🔊

petelouise/abba-8bit-dancing-queen

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 • 35 runs

🤖 Model 🔊

zoharbarzilai/barzil.ai_drumtransfer

Generate or transform drum loops from a text prompt and optional input audio. Set BPM and bar length to control loop tim...

🔊 • music-generation • audio-to-audio • drum-generation • 72 runs

🤖 Model 🔊

andreasjansson/musicgen-trance

Generate late-90s trance music from a text prompt, with optional audio conditioning and continuation. Input a descriptiv...

🔊 • music-generation • audio-to-audio • trance • 126 runs

🤖 Model 🔊

sakemin/musicgen-newjeans

Generate NewJeans-style K-pop music from a text prompt. Fine-tuned MusicGen model trained on NewJeans. Optionally condit...

🔊 • music-generation • audio-to-audio • 99 runs

🤖 Model 🔊

lucataco/mvsep-mdx23-music-separation

Separate songs into individual stems (vocals, bass, drums, other) from a single audio input. Returns isolated tracks for...

🔊 • music-source-separation • audio-to-audio • 21.3K runs

🤖 Model 🔊

vinnie329/musicgen-lora

Generate music from a text prompt or continue a reference audio clip. Accepts a natural-language prompt for genre, mood,...

🔊 • music-generation • audio-to-audio • 63 runs

🤖 Model 🔊

musicly-ai/singing_voice_conversion

Convert a recorded singing voice to sound like a chosen target singer. Input a singing audio clip and select a target fr...

🔊 • audio-to-audio • voice-conversion • 579 runs

🤖 Model 🔊

nateraw/musicgen-songstarter-v0.1

Generate short music ideas and loops from a text prompt, or continue/mimic an input audio clip. Accepts natural-language...

🔊 • music-generation • audio-to-audio • 590 runs

🤖 Model 🔊

ardianfe/music-gen-fn-400e

Generate background music and instrumentals from a text prompt. Optionally condition on an input audio clip to mimic its...

🔊 • music-generation • audio-to-audio • background-music • 259 runs

🤖 Model 🔊

sakemin/musicgen-newjeans-vocals

Generate K-pop-style music with vocal-like elements from a text prompt. Optionally condition on an input audio clip to m...

🔊 • music-generation • audio-to-audio • 275 runs