Unverified50% confidenceFactExact time
After quantization, SteerTTS edge retains 12 control dimensions (speaking rate, loudness, pitch, pitch range, sentence-end rise, pause, tilt, breathiness, etc.), each retaining at least 95% of the fp32 version's control effect.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/22/2026
First Seen
Valid until: 1/20/2027
Sources
Related Entities
Related Claims
UnverifiedSteerTTS edge's weights are dequantized to fp32 on load, so this version saves size rather than inference speed, unless operator kernels are rewritten for edge devices.78% similarUnverifiedSteerTTS edge does not support voice cloning, free-text prompting, or the flow refiner on-device; these capabilities are retained in the full model.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1087455API
curl https://kongchang.com/api/v1/knowledge/claims/1087455MCP
get_claim(id=1087455)