StepFun
StepFun
Speech model · China ·Feb 2025

Step-Audio-TTS-3B

Speech Open (Restricted)
3B
Parameters

About Step-Audio-TTS-3B

Step-Audio-TTS-3B is an AI model developed by StepFun, in the speech category, released in 2025, made available as an open-weights model with 3B params.

On this page you'll find Step-Audio-TTS-3B's full specifications. Review provider pricing and benchmark scores below, or compare Step-Audio-TTS-3B head-to-head with other speech models.

→ More models by StepFun → All speech models → AI benchmarks leaderboard

Links

Announcement ↗ Hugging Face ↗

Run Step-Audio-TTS-3B locally — what fits

GPUs with enough VRAM to hold Step-Audio-TTS-3B at FP16 (lower precision needs less), from best value to most headroom. Generation speed depends on your tool, resolution and step count, so we don't estimate it.

Good
Intel Arc B580 12GB
Consumer GPU · ~$249
12 GB VRAM
fits at FP16 · ~3.5 GB headroom
See fit detail →
Better
AMD Ryzen AI Max+ 395
Consumer GPU · ~$1,999
128 GB VRAM
fits at FP16 · ~107.7 GB headroom
See fit detail →
Best
Apple M2 Ultra 192GB
Apple · ~$6,600
192 GB VRAM
fits at FP16 · ~165.3 GB headroom
See fit detail →

VRAM fit only — we don't estimate generation speed for image/video/audio models (it depends on the tool, resolution and steps).

Consumer GPU
28 options that fit
→
Apple
17 options that fit
→
Datacenter GPU
13 options that fit
→

Community

Would you run Step-Audio-TTS-3B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Step-Audio-TTS-3B

AI
OuteTTS-0.1-350M
· 350M
 AI
SeedLLM
· 7B
 AI
Weight Decay
· 8.4K
 StepFun
Step 3.7 Flash
StepFun · 198B
 StepFun
StepAudio 2.5 Realtime
StepFun
 StepFun
Step-Audio-R1.5
StepFun

Frequently asked questions

What is Step-Audio-TTS-3B? ▶

Step-Audio-TTS-3B is an AI model developed by StepFun, in the speech category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Step-Audio-TTS-3B? ▶

Step-Audio-TTS-3B was developed by StepFun and released in 2025.

Is Step-Audio-TTS-3B open source or proprietary? ▶

Step-Audio-TTS-3B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Step-Audio-TTS-3B cost? ▶

Pricing for Step-Audio-TTS-3B depends on the provider. See the providers table on this page for the latest API rates.

How does Step-Audio-TTS-3B perform on benchmarks? ▶

Benchmark scores for Step-Audio-TTS-3B are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

No videos yet. Know a good one? Add it below.

Know a great video about Step-Audio-TTS-3B?