Weights aren’t public. Use is governed by StepFun’s terms. Specs from models.dev, last changed Oct 18, 2026. Official source: platform.stepfun.ai.
How good is it?
Public leaderboard scores for StepAudio 2.5 TTS, refreshed daily from Epoch AI and LMArena.
No public leaderboard lists StepAudio 2.5 TTS yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.
Where to run it
2 providers sell StepAudio 2.5 TTS through an API. Prices are per million tokens, cheapest first.
From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.
More from StepFun
StepFun
Step 5 Preview
CTX1.02M
Preview
83Quality
Reasoning · Vision · Tools
TextImageVideoInput$1/M
TextOutput$2.70/M
StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window
PaidProprietary1006/1040
StepFun
Step 3.7 Flash
CTX256K
Reasoning · Vision · Tools
TextImageVideoInput$0.18/M
TextOutput$1.11/M
Newer StepFun flash model for faster agents, coding, and multimodal prompts
Open weightsApache 2.0910/1040
StepFun
StepAudio 2.5 ASR
CTX—
Speech to text
AudioInput—
TextOutput—
Speech transcription model for accurate audio-to-text and captioning workflows
PaidProprietary893/1040
StepFun
Step 3.5 Flash 2603
CTX256K
Reasoning · Tools
TextInput$0.10/M
TextOutput$0.30/M
StepFun flash model for efficient multimodal reasoning, coding, and tool use
Open weightsApache 2.0853/1040
StepFun
Step TTS 2
CTX—
Text to speech
TextInput—
AudioOutput—
Speech generation model for controllable voice, narration, and audio delivery
PaidProprietary811/1040
StepFun
Step 3.5 Flash
CTX256K
64Quality
Reasoning · Tools
TextInput$0.10/M
TextOutput$0.30/M
StepFun flash lane for quick multimodal reasoning and coding assistance
Open weightsApache 2.0768/1040
StepFun
Step 2 (16K)
CTX16K
Tools
TextInput$5.21/M
TextOutput$16.44/M
StepFun flash model for efficient multimodal reasoning, coding, and tool use
PaidProprietary468/1040
StepFun
Step 1 (32K)
CTX33K
Tools
TextInput$2.05/M
TextOutput$9.59/M
StepFun flash model for efficient multimodal reasoning, coding, and tool use