StepAudio 3 Realtime Preview
StepAudio 3 Realtime PreviewCompare inon
StepAudio 3 Realtime Preview measured on 3 of 34 Realtime benchmarks3
BenchmarkByScoreRank
Legacy · saturated or no longer reported2
No benchmark matches
free API onlyprice
8.8 sfirst audio?
8.8Time to first audio
—released
Alternatives?
ModelScoreCostPriceWhat changes
BetterGPT Live 1low×7.1—$0.05KOpenRaon SpeechChat 9B×201——
BetterEleven Realtime v1 Max×15.6—$0.08BetterEleven Realtime v1 Mini×14.2—$0.08
BetterGrok Voice 2.0unstated×12.6—$0.08ModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
GPT Live 1low×7.1—$0.05Eleven Realtime v1 Max×15.6—$0.08Eleven Realtime v1 Mini×14.2—$0.08Grok Voice 2.0unstated×12.6—$0.08Grok Voice 3.0×10.8—$0.08ModelScoreCostPriceWhat changes
KRaon SpeechChat 9BOpen×201——
Qwen3 Omni 30B A3B InstructunstatedOpen×10——Step-Audio R1.1Open×5.8——Benchmarks
in Speech & VoiceFull-Duplex-Bench · AA subset v1/v1.598.9#1
Time to first audio · AA8.8#25
FAQ
How much does StepAudio 3 Realtime Preview cost?›
There is no per-unit API price: free API only.
Is StepAudio 3 Realtime Preview free to use?›
Yes, there is a free API option.
How good is StepAudio 3 Realtime Preview, and what is it best at?›
#25 of 25 in Realtime.
Is StepAudio 3 Realtime Preview better than Qwen 3.5 Omni Plus Realtime?›
On Time to first audio · AA, StepAudio 3 Realtime Preview scores 8.8 vs 2.6 — lower.
What is StepAudio 3 Realtime Preview?›
StepAudio 3 Realtime Preview is a speech & voice model from StepFun.
What are the best alternatives to StepAudio 3 Realtime Preview?›
GPT Live 1 (better), Raon SpeechChat 9B (open weights).