Unverified50% confidenceCautionExact time
SteerTTS 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter 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.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.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1087464API
curl https://kongchang.com/api/v1/knowledge/claims/1087464MCP
get_claim(id=1087464)