AudioLDM 2
audioldm-2Latent-diffusion model for general-purpose text-to-audio. Generates speech, music, and sound effects with a unified prior.
- Price
- ≈ $0.0157/run
- Input → output
- Text → Audio
- Developer
- Haohe Liu
- Updated
- September 23, 2026
Playground
Try AudioLDM 2
No input form
No input form for this model yet
Its inputs are not documented yet. So that no run fails on a wrong input, we don't offer a form here. Pick a comparable model instead.
Examples
- Length: 0:05
Prompt
two starships are fighting in space with laser cannons
Settings
- duration
- 5.0
- Length: 0:05
Prompt
a hammer hits a wooden surface
Settings
- duration
- 5.0
- Length: 0:05
Prompt
catchy upbeat pop music, kick drum, bouncy
Settings
- duration
- 5.0
About AudioLDM 2
AudioLDM 2 is a model by Haohe Liu in the Text-to-speech category. On Railwail, AudioLDM 2 costs ≈ $0.0157 per run.
Pricing
| Typical run (≈ 58 s on T4) | $0.0157 per run |
|---|---|
| GPU time (T4) | $0.00027 per GPU second |
- Billed by the GPU time the run actually takes. When the run starts, 3× the typical price is reserved from your balance and settled afterwards.
- 1 credit = $0.01
Cost calculator
Price calculator
Typical according to the provider: about 57.8 s
Total
$1.57
157 credits
Per run
$0.0157 · 1.57 credits
Billed by the actual GPU time; this is an estimate.
API
No verified API example
The inputs of this model are not documented yet.
Specifications
- Model ID
audioldm-2- Developer
- Haohe Liu
- Category
- Text-to-speech
- Input
- Text
- Output
- Audio
- Billing
- By usage (tokens or GPU time)
- Catalog entry updated
- September 23, 2026
Tags
- audioldm
- music-generation
- diffusion
- open-weights
Use cases
Frequently asked questions
What is AudioLDM 2?
AudioLDM 2 is a model by Haohe Liu in the Text-to-speech category.
How much does AudioLDM 2 cost on Railwail?
On Railwail, AudioLDM 2 costs ≈ $0.0157 per run. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals $0.01.
How fast is AudioLDM 2?
There are not enough measured runs of AudioLDM 2 on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.
Is AudioLDM 2 better than Chatterbox?
That depends on the task. AudioLDM 2 (Haohe Liu) and Chatterbox (Resemble AI) are both models in the Text-to-speech category. The comparison page shows their prices and specifications side by side.
Compare AudioLDM 2 and ChatterboxComparable models
All in this category- Kokoro TTS 82MCommunity
Open-weights 82M-parameter TTS. Punches above its size class on naturalness benchmarks at a fraction of the inference cost of larger models.
- OpenVoice v2Community
MyShell OpenVoice v2. Multilingual zero-shot voice cloning with accurate tone-color reproduction and style/emotion control.
- Parler-TTSCommunity
Hugging Face Parler-TTS Mini. Lightweight TTS conditioned on a natural-language style description for fine-grained control over voice characteristics.
All models through one API
One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = $0.01.