VoxMel — Zero-Shot Speech Synthesis

Benchmark

Main Results on Zero-Shot TTS

Zero-shot voice cloning on the Seed-TTS-eval benchmarks. VoxMel is the 690M supervised model; VoxMel + GRPO adds frozen-head GRPO post-training. Both decode with 32 solver steps at guidance (3.5, 3.0).

12 prompts · 8 systems

Seed-TTS test-en

ENGLISH

Prompt	Text	VoxMel	VoxMel + GRPO	VoxCPM-Emilia	VoxCPM	MaskGCT	CosyVoice 2	IndexTTS 2
	After his execution Ogilvie's followers were rounded up and put in jail.
	Rooftop Mounted for homes with no attics.
	He later worked as a journalist, and then became a novelist and playwright.
	Images of the pre-rendered cinematics also began to appear at this time.
	Over time the couple has four more children, although William never warms to them.
	Some transferred the conclusion to Ibsen, his translators and his director.

Scroll horizontally to compare all systems.

Seed-TTS test-zh

CHINESE

Prompt	Text	VoxMel	VoxMel + GRPO	VoxCPM-Emilia	VoxCPM	MaskGCT	CosyVoice 2	IndexTTS 2
	因为眼前奥斯比约恩的鱼篓里，就躺着一个活生生的小人。
	毒虫把毒品丢进马桶冲走，未料毒品又浮出水面，让警方逮个正着。
	人们建造了一座带教堂的医院，奉献给圣约然。
	本文旨在以苏联解体后，陆续解密的档案材料为根据。
	在妙手盘丝环节中，男嘉宾需要两位尖果选手盘发。
	一点五公里后，右转驶入京藏高速辅路。

Scroll horizontally to compare all systems.

Voice Cloning

Same-Language & Cross-Lingual Comparison

Each reference voice is used for both same-language and cross-lingual synthesis. Compare how VoxMel preserves speaker identity while switching between Chinese and English.

6 prompts · 12 samples

English reference voices

EN → EN / ZH

Reference prompt	Same-language text (EN)	VoxMel · Same	Cross-lingual text (ZH)	VoxMel · Cross
	I don't really care what you call me. I've been a silent spectator, watching species evolve, empires rise and fall. But always remember, I am mighty and enduring. Respect me and I'll nurture you; ignore me and you shall face the consequences.		顿时，气氛变得沉郁起来。乍看之下，一切的困扰仿佛都围绕在我身边。我皱着眉头，感受着那份压力，但我知道我不能放弃，不能认输。于是，我深吸一口气，心底的声音告诉我：“无论如何，都要冷静下来，重新开始。”
	Perhaps they are driven by the delicious blend of flavors, or it could be the appealing visual presentation. At the end of the day, our choices in food reflect our personal preferences and sometimes, even our lifestyle or belief system.		我抬起头，坚定地说：“身高不能决定一切，这世界在看我，我更看得到世界。无论是北上广，或是别的什么，我都将以我自己的方式去攀爬，去追逐。我可能小，但我绝不会被忽视。”
	Your safety and the pack's reputation are at stake. Your bravery is admirable, but sometimes bravery is knowing when to retreat. Please, consider returning with me. We can work out a plan, but only if you're willing to listen.		你的勇敢令人钦佩，但有时候勇敢在于懂得何时撤退。拜托，考虑一下和我一起回去吧。我们可以制定一个计划，但前提是你愿意倾听。

Chinese reference voices

ZH → ZH / EN

Reference prompt	Same-language text (ZH)	VoxMel · Same	Cross-lingual text (EN)	VoxMel · Cross
	我看着他们，意气风发地挺直了胸膛，甩了甩那稍显肉感的双臂，轻笑道：“我身上的肉，是为了掩饰我爆棚的魅力，否则，岂不吓坏了你们呢？”		Suddenly, there was a burst of laughter beside me. I looked at them, stood up straight with high spirit, shook the slightly fleshy arms, and smiled lightly, saying, “The flesh on my body is to hide my bursting charm. Otherwise, wouldn't it scare you?”
	顿时，气氛变得沉郁起来。乍看之下，一切的困扰仿佛都围绕在我身边。我皱着眉头，感受着那份压力，但我知道我不能放弃，不能认输。于是，我深吸一口气，心底的声音告诉我：“无论如何，都要冷静下来，重新开始。”		Suddenly, the atmosphere became gloomy. At first glance, all the troubles seemed to surround me. I frowned, feeling that pressure, but I know I can't give up, can't admit defeat. So, I took a deep breath, and the voice in my heart told me, “Anyway, must calm down and start again.”
	皇上的面色未变，宛如雕塑般静止，他的眼中闪过一丝动人的温度。他深深地看了那位忠心耿耿的臣子一眼，终于开口：“诺，我会再考虑考虑的。”他的声音低沉且坚定，留下空气中隐隐的无奈与柔情。		The emperor's complexion did not change, remaining as still as a sculpture, and a touch of touching warmth flashed in his eyes. He deeply glanced at the loyal minister, and finally spoke: “Well, I will consider it again.” His voice was low and firm, leaving a faint hint of helplessness and tenderness in the air.

Scroll horizontally to compare same-language and cross-lingual outputs.

Listen & Explore

More Synthesized Samples

Additional expressive zero-shot synthesis samples. Each card includes the reference prompt, generated speech, and switchable waveform and Mel-spectrogram views.

12 samples · Waveform + Mel

English · 01Happy

I never thought I’d see you here again, but now that you’re standing in front of me, all those old memories suddenly feel wonderful.

Reference prompt