Every option in the catalog for when you need to make a full song or backing track from a prompt — 28 AI music and audio generators, 28 of them free or freemium, with the pricing tier printed on every row.
Flocci AI Tools lists 28 of them, ordered free tiers first: Podcastfy, Riffusion, Treblo (formerly Sonauto), YuE and ACE-Step. Every one of them is free or has a free tier. Each entry states what it uniquely does rather than a score.
14 on this page are marked fully free with no paid plan at all: Podcastfy, Riffusion, Treblo (formerly Sonauto), YuE and ACE-Step. The remaining 14 are freemium, trial or paid, and each is labelled with its exact tier so nothing surprises you at sign-up.
Free tools first, then freemium, then trial, then paid, and alphabetically inside each tier. Nobody pays to appear higher: Flocci AI Tools carries no ads, no sponsored slots and no paid listings, so the order reflects price and nothing else.
Podcastfy, Riffusion, Treblo (formerly Sonauto), YuE and Adobe Podcast Enhance Speech all work in a browser tab with no install needed — just open the site and go. 18 of the 28 free AI music and audio generators listed here are browser-based.
Google Flow Music and Wondercraft support Google sign-in, so you can start without creating a new account. That's 2 of the 28 free AI music and audio generators on this page.
Treblo (formerly Sonauto), Google Flow Music, LALAL.AI, Moises and Mubert have an iOS or Android app. 6 of the 28 free AI music and audio generators here can run on your phone.
ACE-Step, AudioCraft (Meta), Demucs, DiffRhythm and HunyuanVideo-Foley can be self-hosted or run locally without a browser — useful for privacy, air-gapped networks, or avoiding API rate limits. 9 of the 28 free AI music and audio generators here run offline.
| Tool | Pricing | Type | Listed for |
|---|---|---|---|
| Podcastfy | Free | AI Music & Audio | Python package and free HF demo that turns websites, PDFs, images and YouTube into multi-speaker podcasts |
| Riffusion | Free | AI Music & Audio | Riffusion's Producer was acquired by Google and now continues as Flow Music |
| Treblo (formerly Sonauto) | Free | AI Music & Audio | Free AI song generator with vocals from prompts or lyrics, reported without a credit system |
| YuE | Free | AI Music & Audio | Open Apache-2.0 lyrics-to-song foundation model producing multi-minute songs with vocals and accompaniment |
| ACE-Step | Free | AI Music & Audio | Open-weight (Apache-2.0) music foundation model that generates full songs with vocals from text and lyrics |
| AudioCraft (Meta) | Free | AI Music & Audio | Open-source library with MusicGen, AudioGen and EnCodec |
| Demucs | Free | AI Music & Audio | Hybrid Transformer Demucs separates songs into vocals, drums, bass and other stems |
| DiffRhythm | Free | AI Music & Audio | Open-source latent-diffusion model generating full-length songs with vocals in seconds |
| HunyuanVideo-Foley | Free | AI Music & Audio | Generates synced sound effects and ambience for silent video from video plus text description |
| Magenta RealTime | Free | AI Music & Audio | Open-weights live music generation model steered by text or audio prompts |
| MiniMax Music 3 (open weights) | Free | AI Music & Audio | Open-weights model producing full songs up to five minutes from lyrics with section tags and a style description |
| MMAudio | Free | AI Music & Audio | Generates synchronised sound effects for a video and/or text prompt (video-to-audio and text-to-audio) |
| Stable Audio Open | Free | AI Music & Audio | Open-weight text-to-audio model for sound effects, samples and short music clips |
| Ultimate Vocal Remover | Free | AI Music & Audio | Free desktop GUI bundling multiple separation models (MDX-Net, Demucs, VR) |
| Adobe Podcast Enhance Speech | Freemium | AI Music & Audio | Turns noisy voice recordings into studio-quality speech |
| AIVA | Freemium | AI Music & Audio | AI composer for soundtracks and scores |
| Auphonic | Freemium | AI Music & Audio | Automatic leveling, loudness normalization, noise reduction and speech recognition for podcasts and videos |
| Beatoven.ai | Freemium | AI Music & Audio | Fairly Trained certified — musicians compensated for training data |
| ElevenLabs Music | Freemium | AI Music & Audio | Strikingly realistic vocals with breath & vibrato |
| Google Flow Music | Freemium | AI Music & Audio | Full songs with vocals and lyrics from text using DeepMind Lyria 3 / 3.5 |
| LALAL.AI | Freemium | AI Music & Audio | Splits up to 8+ stems (vocals, drums, bass, guitar, piano, strings, wind) not just vocals/instrumental |
| Moises | Freemium | AI Music & Audio | AI Studio generates new musical stems context-aware to an existing track |
| Mubert | Freemium | AI Music & Audio | Splits into 4 products: Render (creators), API (developers), Studio (musician royalties), Play (infinite listening app) |
| Mureka | Freemium | AI Music & Audio | Generates full songs with vocals plus separate stem downloads for DAW use |
| Soundraw | Freemium | AI Music & Audio | Bar-level editing of generated tracks without needing a DAW |
| Suno | Freemium | AI Music & Audio | Full songs with vocals from a text prompt |
| Udio | Freemium | AI Music & Audio | Generate songs with vocals from a text prompt |
| Wondercraft | Freemium | AI Music & Audio | Generates podcasts, audio ads and narration from text, URLs or ideas with 1,000+ AI voices |