Text-to-Speech
Transformers
Safetensors
Qwen3-TTS
English
Chinese
text-generation
zen3
zen3-tts
zenlm
qwen3-tts
speech-synthesis
voice-cloning
12hz
Instructions to use zenlm/zen3-tts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenlm/zen3-tts with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="zenlm/zen3-tts")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("zenlm/zen3-tts", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add NOTICE: Copyright Zen Authors
Browse files
NOTICE
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Zen
|
| 2 |
+
Copyright 2025-2026 Zen Authors
|
| 3 |
+
|
| 4 |
+
This model and its accompanying code are licensed under the Apache License, Version 2.0.
|
| 5 |
+
Zen models are developed by the Zen Authors (https://zenlm.org).
|
| 6 |
+
|
| 7 |
+
This model is derived from an upstream base model (Qwen3-TTS-12Hz-1.7B-Base),
|
| 8 |
+
distributed under a compatible permissive license. Upstream
|
| 9 |
+
attribution is retained as required by that license.
|