gradium/phonon-voices
archived · low-signalmodel
Each voice is a .safetensors embedding that Phonon uses directly, with no cloning (format ba7a5a45@300: one tensor speakerwavs, 1×512×125, float32). License: apache-2.0.
- Org
- gradium
- Released
- 2026-10-19
- Status
- archived · low-signal
- License
- apache-2.0 (permissive)
- Signal
- 15 HF likes · 0 downloads
- Archived
- 2026-10-24 (low-signal: aged out below threshold; stats as last seen)
Links
First published here 2026-10-19 · updated 2026-10-25 · markdown · JSON