Qwen/Qwen3-TTS-12Hz-1.7B-Base
no scores extracted for this variant.
| title | author | status | comments | type |
|---|---|---|---|---|
| Соня | orbit5031067 | open | 0 | disc |
| GGUF + pure-C++ runtime in CrispASR — Qwen3-TTS-1.7B (larger talker) | cstr | open | 0 | disc |
| Voice clone | Alim02 | draft | 0 | disc |
| Dual-Reference Voice Synthesis (Timbre + Prosody separation) | Nanni61 | open | 0 | disc |
| Add GGUF convertation support | Naster17 | open | 0 | disc |
| How to make the model speak slower? | nitin19 | open | 0 | disc |
| Impressive, but need more control for text to speech | AnykeyNL | open | 0 | disc |
| How to insert "pause" ? | ziobuddagmail | open | 0 | disc |
| Add metadata tags | nielsr | open | 0 | disc |
| Qwen3‑TTS‑12Hz‑1.7B‑Base pronounces “he’s” as “his” in English | russellbal | open | 0 | disc |
| Nomenclature | anujchopra | closed | 0 | disc |
| 8G不能玩吗？本地加载报错 | TJundx | open | 0 | disc |
| Can't Stream With The Model Locally | Sarkkoth77 | open | 0 | disc |
| Add pipeline tag, paper link, and sample usage | nielsr | closed | 0 | disc |
| Representing laughs and other speech cues | acatovic | open | 0 | disc |
| speech to speech possible? | krigeta | open | 0 | disc |