audio-to-audio AI Models

🤖 Model 🔊

justmalhar/musicgen-lofi-gaming

Generate lofi gaming beats from a text prompt. Optionally condition on an input audio clip to mimic its melody or create...

🔊 • music-generation • audio-to-audio • lofi • 242 runs

🤖 Model 🔊

fofr/musicgen-tron

Generate Tron-style electronic music from a text prompt. Optionally condition on an input audio clip to mimic its melody...

🔊 • music-generation • audio-to-audio • 182 runs

🤖 Model 🔊

ardianfe/musicgen-ft

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

🔊 • music-generation • audio-to-audio • 66 runs

🤖 Model 🔊

fofr/musicgen-slipknot

Generate Slipknot-style heavy metal music from a text prompt or a reference audio clip. Condition generation with an inp...

🔊 • music-generation • audio-to-audio • 169 runs

🤖 Model 🔊

jagilley/free-vc

Convert spoken audio to a target speaker’s voice using a reference sample. Provide a source audio file (content) and a r...

🔊 • audio-to-audio • voice-cloning • 76.0K runs

🤖 Model 🔊

datasci888/musicgen

Generate music from a text prompt or transform an input audio file by continuing it or mimicking its melody, returning a...

🔊 • music-generation • audio-to-audio • 74 runs

🤖 Model

sakemin/musicgen-toad

Generates music from text prompts, fine-tuned specifically to create cover songs in the style of Toad from the Super Mar...

music-generation • 61 runs

🤖 Model 🔊

naclonts/musicgen-experiment-1

Generate Moog synthesizer–style music from a text prompt or by continuing/mimicking an input audio clip. Use a MusicGen...

🔊 • music-generation • audio-to-audio • moog-synth • 48 runs

🤖 Model 🔊

sakemin/musicgen-bbongjjak

Generate Bbongjjak (뽕짝) music from a text prompt or an input audio reference. Create Korean Trot-influenced, modern elec...

🔊 • music-generation • audio-to-audio • 91 runs

🤖 Model 🔊

tabstle/soad_music_gen

Generates music in the style of System of a Down using text prompts and optional audio input. Fine-tuned from MusicGen,...

🔊 • music-generation • audio-to-audio • 31 runs

🤖 Model 🔊

sakemin/musicgen-pansori

Generate Pansori (Korean traditional folk epic chant) music from a text prompt, with optional audio conditioning or cont...

🔊 • music-generation • audio-to-audio • pansori • 35 runs

🤖 Model

justmalhar/musicgen-flute-artist

Generates music from text prompts using MusicGen Small fine-tuned specifically on Bollywood-style flute covers. Supports...

music-generation • 72 runs

🤖 Model 📝 → 🔊

cjwbw/voicecraft

Performs zero-shot speech editing and text-to-speech synthesis using audio input and text transcripts. Supports four mai...

📝 → 🔊 • text-to-speech • voice-cloning • audio-to-audio • 11.2K runs

🤖 Model 🔊

zsxkib/realistic-voice-cloning

Create song covers by cloning voices from audio files using RVC v2 technology. Takes an input audio file and transforms...

🔊 • voice-cloning • audio-to-audio • 2.0M runs

🤖 Model 📝 → 🔊

usamaehsan/voices

Generate speech from text and convert voices. Use zero_shot voice cloning to synthesize speech in the style of a prompt_...

📝 → 🔊 • text-to-speech • voice-cloning • audio-to-audio • 877 runs

🤖 Model 🔊

pseudoram/rvc-v2

Convert speech to a target voice using RVC v2 voice models. Takes an input speech audio clip and outputs converted audio...

🔊 • audio-to-audio • voice-cloning • speech-style-transfer • 1.1M runs

🤖 Model 🔊

fofr/musicgen-livestock-auctioneer

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

🔊 • music-generation • audio-to-audio • 43 runs

🤖 Model 📝 → 🔊

ictnlp/llama-omni

Answer spoken queries with simultaneous text and speech output. Accepts a speech audio input and an optional instruction...

📝 → 🔊 • text-to-speech • text-generation • voice-assistant • 60.1K runs

🤖 Model 🔊

zoharbarzilai/drumtest2

Transform rhythmic audio or video into acoustic drum performances. Input beatboxing, hand drumming, toy drums, or other...

🔊 • audio-to-audio • music-generation • drums • 32 runs

🤖 Model 🔊

illscience/dreaminaudio

Generate West Coast house music from a text prompt. Optionally condition on an input audio clip to continue it from a ch...

🔊 • music-generation • audio-to-audio • 135 runs