Deploy FunAudioLLM models on dedicated GPUs
1 FunAudioLLM model ready to deploy on GPU capacity reserved for you, from — parameters, covering text-to-speech. Private OpenAI-compatible endpoint, European GPUs, billed per GPU-hour.
| Model | Type | Params | Context | License |
|---|---|---|---|---|
| FunAudioLLM | Text-to-speech | — | — | Apache 2.0 |
Specs from Hugging Face, synced 2026-10-27. Machine-readable version: https://sference.com/models/FunAudioLLM.md
FAQ
Which FunAudioLLM models can I deploy on sference?
1 today, most requested first: Fun-CosyVoice3-0.5B-2512. Any other FunAudioLLM checkpoint or a fine-tune of one can be requested with the form on this page.
How many GPUs do FunAudioLLM models need?
It depends on the model: the lineup runs from — to — parameters. Each model page lists the checkpoint size and the minimum footprint on 80 GB and 141 GB GPUs. You don't pick hardware on sference: you choose a performance tier and we size the deployment.
Can I use FunAudioLLM models commercially?
1 of the 1 listed models are under licenses that allow commercial use (Apache 2.0 across the lineup). Each model page summarizes its license and links the full text.
How is a dedicated deployment priced?
Per GPU-hour on a monthly commitment, sized to your throughput and latency targets.
Request a FunAudioLLM model
Tell us which FunAudioLLM model and roughly how much traffic you expect. Fine-tunes of these models work the same way.
- 01We size it
A performance tier, the capacity behind it, and a quote for your volume.
- 02We benchmark it
Bring one workload with a sample of real traffic; we come back with latency and throughput numbers.
- 03It goes live
We provision the deployment. You call it with the same API and model id as before.