name = "Step TTS 2"
description = "Speech generation model for controllable voice, narration, and audio delivery"
family = "step"
release_date = "2026-03-01"
last_updated = "2026-07-02"
attachment = false
reasoning = false
temperature = false
tool_call = false
open_weights = false

[limit]
context = 0
output = 0

[modalities]
input = ["text"]
output = ["audio"]