StepAudio 3 TTS ↗
- source model id
- stepaudio-3-tts
- hosting
- stepfun-global-hosted
- platforms
- StepFun
- architecture
- input_modalities
- text
- output_modalities
- speech
- capabilities
- speechOutput
- streaming
The model closely follows natural human speech in timbre, intonation, rhythm, breathing, and pauses. It can express laughter, hesitation, stutters, repetition, and self-correction while adapting emot…
stepFun/stepaudio-3-tts
The model closely follows natural human speech in timbre, intonation, rhythm, breathing, and pauses. It can express laughter, hesitation, stutters, repetition, and self-correction while adapting emotion and tone to the meaning of the text.
1–1 / 1
1–2 / 2
1–1 / 1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.