model · first seen 16 Oct 2026
Qwen3-TTS
A text-to-speech model from the Qwen family supporting zero-shot voice cloning.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Beyond the Benchmark: Conditioning, Domains and Failure Modes of Qwen3-TTSPapers · 16 Oct 2026 · Séverin Baroudi, Yanis Labrak, Petr Motlicek, Hervé Bredin, Ricard Marxer
Latest sources
- Beyond the Benchmark: Conditioning, Domains and Failure Modes of Qwen3-TTSPapers · 16 Oct 2026 · Séverin Baroudi, Yanis Labrak, Petr Motlicek, Hervé Bredin, Ricard Marxer