Stable AudioSynth Max
NEW HOTStability AI · Other
Open SourceAPI
Stable AudioSynth Max is a generative model capable of creating realistic and expressive audio, music, and speech from text prompts with emotional depth.
TextAudioVideo
Scores 89% on MMLU, competitive across 4 standard benchmarks.
Data aggregated and editorially reviewed by TrendMing.
Benchmark Performance
MMLU89%
HumanEval82%
MATH78%
GPQA86%
Scores sourced from published evaluations. Higher = better.
Quick Specs
Context Window300K tokens
Parameters800B
Input pricing$0.003 / 1K audio-tokens
Output pricing$0.008 / 1K audio-tokens
Released2026-10-03