Qwen3-TTS 1.7B CustomVoice
Alibaba · Qwen
Alibaba's Qwen3-TTS with 9 premium preset voices and instruction-based control over tone, emotion and prosody across 10 major languages. Streaming generation gets end-to-end latency as low as 97ms. Apache 2.0 licensed — fully free for commercial use, unlike most other speech models on this page.
Params
1.7B
License
Apache 2.0
Min VRAM
Not published — FlashAttention recommended to reduce memory use
Speed
End-to-end synthesis latency as low as 97ms (streaming)
Languages
Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian
Tier
Standard
Install & run locally
pip install -U qwen-tts
from qwen_tts import Qwen3TTSModel
model = Qwen3TTSModel.from_pretrained(
"Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice",
device_map="cuda:0",
dtype=torch.bfloat16,
)
wavs, sr = model.generate_custom_voice(text="Sample text", language="English", speaker="Ryan")Full install and usage docs on the Hugging Face model card.
Will it run on my hardware?
Qwen3-TTS 1.7B CustomVoice needs about Not published — FlashAttention recommended to reduce memory use of fast memory. Here is what in our hardware database clears that bar.
Memory requirement for this model is variable — see the run command and the model notes above.
Hardware links are affiliate links. We earn a small commission if you buy through them — at no extra cost to you. Disclosure
Specifications
| Parameters | 1.7B |
|---|---|
| License | Apache 2.0 |
| Min VRAM | Not published — FlashAttention recommended to reduce memory use |
| Speed | End-to-end synthesis latency as low as 97ms (streaming) |
| Languages | Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian |
| Recommended tier | Standard |
| Best for | custom voicevoice cloningmultilingual speech |
Source
Not distributed through Ollama — install and run it directly from the model card.
View on Hugging FacePopularity trend (illustrative)
Illustrative adoption trend, not actual download counts. We do not publish a download number for any model because we have no honest source for it.
Similar models
Fish Audio S2 Pro
Fish Audio · Fish Audio Research License (non-commercial)
Fish Audio's flagship speech model, trained on 10M+ hours of audio with fine-grained inline control over prosody and emotion across 80+ languages. Needs a 24 GB GPU for CUDA inference, though a CPU-only install path exists for testing. Free for research and non-commercial use under the Fish Audio Research License; commercial use requires a separate paid license.
Min VRAM
24 GB GPU (CUDA) — CPU-only install also available
Speed
Real-time factor 0.195 on a single H200 · time to first audio ~100ms
Install & run
git clone https://github.com/fishaudio/fish-speech.gitBreeze TTS 2
BreezeBlue · BreezeBlue Research Non-Commercial (code: Apache 2.0)
Released August 2026 and currently the #1 open-weight model on the Artificial Analysis speech arena (1,215 Elo). Supports voice cloning from a short reference clip, voice design from a text description, and inline direction tags like (sigh) for emotion. Needs a 12 GB GPU for eager inference or 24 GB for the faster path. Weights are BreezeBlue's Research Non-Commercial license — the code is Apache 2.0, but commercial use requires their paid API.
Min VRAM
12 GB GPU (7.7 GiB eager) / 24 GB GPU (14.4 GiB fast path)
Speed
Time to first audio <40ms · real-time factor 0.32
Install & run
git clone https://github.com/breezeblue-ai/breeze-tts.gitKokoro-82M
hexgrad · Apache 2.0
The most-downloaded text-to-speech model on HuggingFace by a wide margin, at 11.6M downloads a month. At just 82M parameters it is small enough to run on CPU alone — no GPU minimum is published, unlike most other speech models here. Apache 2.0 licensed, so it is fully free for commercial use with no restrictions. Ships with 8 languages and 54 voices out of the box.
Min VRAM
None published — small enough to run on CPU alone
Speed
—
Install & run
pip install -q kokoro>=0.9.2 soundfile