Models tagged "audio-to-audio"

🤖 Model 📝 → 🔊

zsxkib/kimi-audio-7b-instruct

Transcribe speech and generate spoken replies from an audio input. Accepts an audio file (with an optional text prompt)...

📝 → 🔊 • speech-to-text • text-to-speech • audio-to-audio • 3.3K runs

🤖 Model 🔊

cjwbw/audiosep

Separate a target sound from a mixed audio recording using a natural-language text query. Provide an audio file and a de...

🔊 • audio-to-audio • music-source-separation • audio-denoising • 5.4K runs

🤖 Model 🔊

retrocirce/zero_shot_audio_source_separation

Separate a target sound source from a mixed audio track using an example query audio. Takes a mixture audio and a short...

🔊 • music-source-separation • audio-to-audio • 57.0K runs

🤖 Model 🔊

sakemin/audiosr-long-audio

Upsample and restore audio to 48 kHz from lower-quality inputs. Takes an audio file and returns a higher-fidelity audio...

🔊 • audio-to-audio • audio-super-resolution • 2.7K runs

🤖 Model 🔊

fabiwlf/cog-resemble-enhance

Denoise and enhance speech in audio recordings. Takes an audio file as input and outputs a cleaned, enhanced audio file...

🔊 • audio-denoising • audio-to-audio • speech-enhancement • 192 runs

🤖 Model 🔊

ardianfe/stable-audio-prod

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

🔊 • music-generation • audio-to-audio • 69.1K runs

🤖 Model 🔊

meta/musicgen

Generate music from a text prompt or an input melody. Accepts text and/or a reference audio clip and outputs stereo musi...

🔊 • music-generation • audio-to-audio • 3.1M runs

🤖 Model 🔊

fofr/musicgen-choral

Generate choral and choir music from a text prompt, with optional audio conditioning to mimic a melody or continue an in...

🔊 • music-generation • audio-to-audio • 4.7K runs

🤖 Model 🔊

sakemin/musicgen-stereo-chord

Generate stereo music from a text prompt with explicit chord control or from chords extracted from an input audio clip....

🔊 • music-generation • audio-to-audio • chord-conditioned • 3.3K runs

🤖 Model 🔊

sakemin/musicgen-chord

Generate music from a text prompt constrained by chord progressions, BPM, and time signature. Provide chord control as t...

🔊 • music-generation • audio-to-audio • chord-conditioned • 2.9K runs

🤖 Model 🔊

ardianfe/music-gen-fn-200e

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

🔊 • music-generation • audio-to-audio • 1.0M runs

🤖 Model 🔊

sakemin/musicgen-remixer

Remix music into new styles from a text prompt and an input audio track. Generate a new backing track conditioned on the...

🔊 • audio-to-audio • music-generation • music-remixing • 17.6K runs

🤖 Model 🔊

charlesmccarthy/musicgen

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

🔊 • music-generation • audio-to-audio • 1.4K runs

🤖 Model 🔊

sakemin/musicgen-fine-tuner

Generate music from a text prompt, with optional audio conditioning (melody following) or continuation of an input clip....

🔊 • music-generation • audio-to-audio • 10.9K runs

🤖 Model 🔊

ardianfe/ft-melody

Generate music from a text prompt, an input audio reference, or by continuing an audio clip. Accepts a prompt describing...

🔊 • music-generation • audio-to-audio • 262 runs

🤖 Model 🔊

lclrke/musicgen-roxo

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

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

🤖 Model 🔊

ardianfe/stable-audio-staging

Generate music from a text prompt, with optional audio conditioning for melody mimicry or seamless continuation. Accepts...

🔊 • music-generation • audio-to-audio • 287 runs

🤖 Model 🔊

nateraw/musicgen-songstarter-v0.2

Generate stereo music from a text prompt or an input audio reference. Provide a descriptive prompt (genre, instruments,...

🔊 • music-generation • audio-to-audio • 5.1K runs

🤖 Model 🔊

sakemin/musicgen-opn

Generate music from a text prompt with a Oneohtrix Point Never (OPN) fine-tuned style. Accept a text description and opt...

🔊 • music-generation • audio-to-audio • 294 runs

🤖 Model 🔊

richardjiang736/musicgen_lyre_0_new

Generate Ancient Greek lyre instrumentals from a text prompt. Optionally condition on an input audio clip to mimic its m...

🔊 • music-generation • audio-to-audio • 15 runs