text-to-audio AI Models

🤖 Model

smaerdlatigid/stable-audio

Generate audio clips from text prompts with configurable duration up to 60 seconds. Allows control over generation steps...

music-generation • sound-effect-generation • 432 runs

🤖 Model 🔊

gougouccnu/stable-audio-open-1.0

Generates audio from text prompts using the Stable Audio Open 1.0 model. Supports configurable duration up to 47 seconds...

🔊 • music-generation • sound-effect-generation • audio-generation • 667 runs

🤖 Model 📝 → 🔊

declare-lab/tangoflux

Generate audio from a text prompt. Produce 44.1 kHz sound effects and ambiences from natural language with user-set dura...

📝 → 🔊 • text-to-audio • sound-effect-generation • 54.4K runs

🤖 Model 📝 → 🔊

declare-lab/tango

Generate sound effects and general non-music audio from a text prompt. Accepts a textual description and returns an audi...

📝 → 🔊 • text-to-audio • sound-effect-generation • 132.2K runs

🤖 Model 📝 → 🔊

press1209/musicology-v1-beta

Generate short genre-conditioned music from a text prompt. Inputs: prompt text, a genre selector (80s R&B or 90s Hip-Hop...

📝 → 🔊 • music-generation • text-to-audio • 50 runs

🤖 Model 📝 → 🔊

sepal/audiogen

Generate sound effects and environmental audio from text descriptions. Based on Meta's AudioGen from the Audiocraft libr...

📝 → 🔊 • sound-effect-generation • text-to-audio • 152.5K runs

🤖 Model

pphu/musicgen-small

Generate music from a text prompt. Produce up to 30 seconds of instrumental audio by describing genre, mood, tempo, key,...

music-generation • 170 runs

🤖 Model

riffusion/riffusion

Generates music from text prompts using a fine-tuned Stable Diffusion model that creates spectrograms which are then con...

music-generation • 1.1M runs

🤖 Model

pollinations/music-gen

Generates music from text prompts using the MusicGen model. Takes text descriptions and outputs audio files with configu...

music-generation • 15.0K runs

🤖 Model 📝 → 🔊

ardianfe/stable-audio-2

Generates music from text prompts using a fine-tuned version of Stable Audio. Takes text descriptions and produces audio...

📝 → 🔊 • music-generation • text-to-audio • 8.5K runs

🤖 Model

google/lyria-2

Generates 30-second music compositions in 48kHz stereo audio from text prompts. Produces professional-grade audio suitab...

music-generation • 160.6K runs

🤖 Model 📝 → 🔊

haoheliu/audio-ldm

Generate sound effects, human speech, and music from text prompts using latent diffusion models. Supports zero-shot text...

📝 → 🔊 • text-to-speech • sound-effect-generation • music-generation • 43.2K runs

🤖 Model 📝 → 🔊

press1209/musicgen-90s

Generate music from a text prompt. Control style by specifying genre, era (e.g., 90s, 80s), mood, and instruments, and a...

📝 → 🔊 • music-generation • text-to-audio • 32 runs

🤖 Model 📝 → 🔊

fishaudio/ace-step-1.5

Generates music from text prompts describing genre, mood, instruments, and style. Accepts lyrics input or can create ins...

📝 → 🔊 • music-generation • text-to-audio • 40.6K runs

🤖 Model 📝 → 🔊

declare-lab/mustango

Generate music from text prompts with controllable musical features. Uses a Latent Diffusion Model combined with Flan-T5...

📝 → 🔊 • music-generation • text-to-audio • 8.9K runs

🤖 Model 📝 → 🔊

zj7730/test-music

Generates music from text prompts with configurable style, title, and instrumental options.

📝 → 🔊 • music-generation • text-to-audio • 18 runs

🤖 Model 📝 → 🔊

lucataco/magnet

Generates music from text prompts using a non-autoregressive transformer architecture. Offers multiple model sizes (300M...

📝 → 🔊 • music-generation • text-to-audio • sound-effect-generation • 3.2K runs

🤖 Model 📝 → 🔊

google/lyria-3

Generates 30-second music clips from text prompts or up to 10 input images. Supports any genre including pop, jazz, elec...

📝 → 🔊 • music-generation • text-to-audio • image-to-audio • 185.1K runs

🤖 Model 📝 → 🔊

irulkenzei/stable-audio-open

Generates variable-length stereo audio (up to 47 seconds) at 44.1kHz from text prompts. Uses an autoencoder to compress...

📝 → 🔊 • music-generation • sound-effect-generation • text-to-audio • 268 runs