AI Audio & Music Generation Software
AI music, voice, and SFX generation tools.
| Software | Description | License | Tags | Best For |
|---|---|---|---|---|
| ACE Studio | AI singing voice synthesizer with expression control. See also: AI & Machine Learning for CG → AI Audio & Music |
Free tier | Singing · Expression | AI singing synthesis |
| AIVA | AI composition, good for orchestral/cinematic scoring. See also: AI & Machine Learning for CG → AI Audio & Music |
Free tier | Orchestral · Scoring | Orchestral/cinematic scoring |
| DiffRhythm | Open-source full-song gen with vocals from lyrics. See also: AI & Machine Learning for CG → AI Audio & Music |
Open source | Open Source · Lyrics→Song | Open-source song gen with vocals |
| ElevenLabs | Voice cloning, narration, music generation. See also: AI & Machine Learning for CG → AI Audio & Music |
Free tier | Voice Cloning · TTS | Voice cloning, TTS |
| F5 TTS | Open-source zero-shot voice cloning TTS. See also: AI & Machine Learning for CG → AI Audio & Music |
Open source | Zero-Shot · Voice Clone | Zero-shot voice cloning |
| Fish Audio | Open-source TTS with voice cloning, fast and multilingual. See also: AI & Machine Learning for CG → AI Audio & Music |
Open source | Open Source · Multilingual | Open-source TTS |
| HunyuanVideo-Foley (Tencent) | Open model that generates foley audio matched to video and text. See also: AI & Machine Learning for CG → AI Audio & Music |
Free | Free · Tencent | Video foley generation |
| Mirelo | AI sound effects synced to video, with a browser editor, Premiere and Resolve plugins and an API. See also: AI & Machine Learning for CG → AI Audio & Music |
Free tier | Freemium · Web | Synced video sound effects |
| MMAudio | Open model that generates synced sound effects for video or from text. See also: AI & Machine Learning for CG → AI Audio & Music |
Free, non-commercial | Non-Commercial · Video to Audio | Video sound effects |
| Suno v5 | Full song generation, 100M+ users. See also: AI & Machine Learning for CG → AI Audio & Music |
Free tier | Song Gen · 100M users | Full song generation |
| ThinkSound | Open model that generates audio from video, text or audio. Repo also hosts PrismAudio. See also: AI & Machine Learning for CG → AI Audio & Music |
Open source | Open Source · Video to Audio | Audio from video |
| Udio | Strong electronic/pop, licensed for commercial use. See also: AI & Machine Learning for CG → AI Audio & Music |
Free tier | Electronic/Pop · Commercial | Commercial-licensed AI music |