AudioLDM 2
Foundation Models · Free
Latent diffusion model for audio and music generation
At a glance
- Made by
- University of Surrey(CVSSP)·ByteDance(SAMI)
- Korean
- None (English and a few others only)
- Available on
- CLI
- GitHub
- 2,642 stars · NOASSERTION
What is AudioLDM 2?
AudioLDM 2 is a framework that handles speech, music, and sound effect generation with a single training approach. It converts audio into a common representation called the 'language of audio (LOA)', uses GPT-2 to map other modalities into LOA, and then generates audio with a latent diffusion model. It states that it achieved SOTA on text-to-audio and text-to-music, and competitive performance on text-to-speech. You can run it from the command line or as a Gradio web app using the GitHub code.
- Text-to-audio (sound effects) generation
- Text-to-music generation
- Text-to-speech generation
- Super-resolution and inpainting
- 48kHz high-quality checkpoint
- Command-line (audioldm2) execution
- Gradio web app
- Diffusers library integration
Pricing
Open source (free, weights/code released)
Released free under an open-source license with no extra cost for self-hosting (usage-based pricing when offered as a cloud API)
Estimate based on AI knowledge - please verify on the official site
AI tools similar to AudioLDM 2 (alternatives)
AudioLDM 2 vs. alternatives at a glance
| AI | Pricing | Combos on the map | Connected tools | Free | Cheapest monthly | Korean |
|---|---|---|---|---|---|---|
| AudioLDM 2 | Free | 0 | 5 | — | — | No |
| Bark | Free | 0 | 5 | No | — | — |
| Kokoro | Free | 0 | 5 | No | — | — |
| MusicGen | Free | 0 | 5 | — | — | — |
| StyleTTS2 | Free | 0 | 5 | — | — | — |
0 of these 5 tools have a free plan.
Combo and connection counts are based on the relationships recorded on AI Galaxy Map (2026-10-26); they are not a quality ranking.
AudioLDM 2 on AI Galaxy Map
- One of 60 AI tools in the Foundation Models field.
- Connected to 5 other tools — #16 in its field.
Frequently asked questions
Can I use AudioLDM 2 for free?
Open source (free, weights/code released). Prices can change, so check the official site before paying.
What AI can I use instead of AudioLDM 2?
Tools that do the same job, such as Bark, Kokoro, MusicGen, StyleTTS2, are connected to it on the map.
Can I use AudioLDM 2 in Korean?
None (English and a few others only)
Sources (official pages)
Checked on the official pages on 2026-10-14. Prices and features can change, so check the official site again before paying.