SOURCE-REVIEWED MODEL PROFILE
Qwen3-TTS-12Hz-0.6B-Base
The small Qwen3-TTS Base checkpoint supports multilingual speech synthesis from reference voice audio.
Metadata reviewed 2026-10-24 · Original creator: Qwen
What it does
- Local speech synthesis
- External task-specific runtime; not integrated into launcher chat
Local fit
Very small model / edge candidate; runtime validation required. Uses an audio tokenizer and dedicated Qwen TTS runtime. The official Base-model training recipe is single-speaker, separate from text LoRA.
Runtime limits and on-device memory must be validated separately.
Evidence and limits
Source reviewed only. No local model or Android inference test performed.
External task-specific runtime; not integrated into launcher chat
License and source
Review the exact checkpoint, voice assets and applicable upstream notices; model references do not grant new rights.
Read the original model card ↗
Reviewed source revision: 5d83992436eae1d760afd27aff78a71d676296fc