Architecture Overview
Expressiveness Demonstrations
Showcase with High Versatility
| Description | Source Audio | Generated Audio |
|---|---|---|
| A Compelling and Persuasive Speaker Voice | ||
| A Clear and Explanatory Voice with Broad Emotional Dynamics Across Different Texts | ||
|
Another Explanatory Voice with Supernatural Prosody, Featuring Distinct Ethnic and Age Characteristics |
||
| A Warm and Magnetic Voice that Brings Comfort | ||
| An ASMR Whispering Voice with Generated Breathing and Sound Effects | ||
| A Robotic Voice with Rich Bass Resonance and Spatial Presence | ||
| A Sardonic Mature Female Voice |
Showcase with Multiple Generation Attempts, Post-Processing Audio Effects and Added Sound Effects
| Description | Generated Audio |
|---|---|
| A Husky Male Voice: From Soft Murmur to Excitement to Anger, then to Whispers | |
| An Angry Female Voice: From Soft Murmur to Rage to Reminiscence, then to Weeping |
Zero-Shot vs. One-Shot Demonstrations
ZeroShot maintains speaker identity while generating more natural emotions, pauses, and other expressive features based on the text content, whereas OneShot adheres more strictly to the speaker characteristics (prosody, speech rate, emotions, etc.) demonstrated in the audio prompt (The additional input that OneShot has compared to ZeroShot, see technical report for details).
| Source Audio | Text | Zero-Shot Version | One-Shot Version | Elevenlabs Multilingual_v2 |
|---|---|---|---|---|
|
命运就算颠沛流离， 命运就算曲折离奇， 命运就算恐吓着你， 做人没趣味。 别流泪，心酸，更不应舍弃。 我愿能，一生永远陪伴你。 |
Preserving Distinctive Voice Timbre and Expressive Prosody with Regularized Pausing and Speech Rate |
Better Reproduction of Prompt's Exaggerated Speech Rate and Characteristic Phrase-Initial Pauses |
Cantonese not supported | |
|
你们这些躲在道德高地的懦夫， 敢承认自己对本我的恐惧吗？ 回答我！嗯？你回答我！ Look in my eyes！ 老子写梦的解析时 你们还在玩泥巴， 我精神分析引论每个字母都能 刺穿文明社会的虚伪面具， 我解剖潜意识就像 外科医生划开皮肤。 是不是啊？说话！ |
Capable of Generating Relatively Calmer Emotions while Preserving Voice Identity |
Consistently Reproducing the Angry Emotion from Prompt in Every Utterance |
||
|
Would you believe what happened at the grocery store today? My goodness! The avocados were on sale - half price! Half price! I bought twenty of them! |
Effectively follows textual cues for both longer and shorter inter-sentence pauses |
Better reproduces the exaggerated high pitch characteristic of anime voices |
||
|
Oh my gosh, like, I literally can't believe what just happened! Um, so basically, I was, you know, just sitting there in class, right? And then, ugh, this totally weird thing happened - like, seriously weird! Wait, wait... Should I even be talking about this? Ugh, whatever. |
Effectively follows textual cues for both longer and shorter inter-sentence pauses |
Better reproduces the exaggerated high pitch characteristic of anime voices |
Multilingual and Cross-Lingual Capabilities Demonstrations
Speech-02-HD maintains high naturalness in less common languages while demonstrating significant advantages in Standard Chinese pronunciation accuracy.
| Languages | Source Audio | Text | MiniMax Speech_02_HD |
ElevenLabs Multilingual_v2 |
OpenAI TTS_1_HD (*not cloned voice) |
|---|---|---|---|---|---|
| Thai |
สวัสดีค่ะ วันนี้อากาศดีมากเลย คุณจะไปทานอาหารกลางวันที่ไหนคะ ฉันกำลังคิดว่าจะไปร้านอาหารไทยแถวนี้ |
Thai not perfectly supported | |||
| Vietnamese |
Tôi đang đọc một cuốn sách rất hay về lịch sử Việt Nam. Những câu chuyện về văn hóa truyền thống thật sự rất thú vị. |
Vietnamese not perfectly supported | |||
| Czech |
Ranní mlha se pomalu zvedá nad řekou, zatímco první paprsky slunce prosvítají mezi stromy. Ptáci začínají svůj ranní koncert. |
||||
| Polish | 、 |
Młoda sowa siedzi cicho na gałęzi sosny, obserwując leśną polanę w świetle księżyca. Wiatr delikatnie porusza liśćmi drzew. |
|||
| Japanese |
電車が遅延している影響で、渋谷駅がとても混雑 しています。次の山手線は約10分後に到着 予定です。お急ぎのお客様は、他の路線も ご利用ください。 |
Speech-02-HD has superior performance in zero-shot cross-lingual scenarios.
| Original Language | Source Audio | Mixed Language | Text | MiniMax Speech_02_HD |
ElevenLabs Multilingual_v2 |
OpenAI TTS_1_HD (*not cloned voice) |
|---|---|---|---|---|---|---|
| English | English + Mandarin |
Kiddo! Come come come, 学如逆水行舟，不进则退。 I see you're using AI tools already - so smart! But eh, cannot just rely on tools only lah! The future belongs to those who can work alongside AI, not those scared of it. |
||||
| Mandarin | Mandarin + Cantonese |
老铁啊，多谢晒你送我呢本，广州话正音字典，咁好嘢喎！ 我呢个大老爷们儿学广州话真系好难㗎！成日都分唔清声调啊。 嗱，而家有咗呢本书，什么都好啦。 |
Cantonese not supported | Cantonese not supported | ||
| Mandarin | Mandarin + English |
The people said, 桂林's scenery is the first under heaven. Yet in my opinion, 阳朔 scenery is better than 桂林。 群峰倒影山浮水，无水无山不入神。 |
||||
| English | English + Spanish |
Mi abuelita always told me "el que persevera, alcanza". If you persevere, you'll achieve your dreams! Guess what! They choose me to play the lead role in our BIG show! |
||||
| Japanese | Japanese + Korean |
最近の天気予報によりますと、今週末は桜の開花に最適 な気温になる予定です。 東京都内の各公園では花見客で賑わうことが予想されますが、 서울에서도 벚꽃이 피기 시작했다고 하네요. 이번 주말에는 여의도 공원에서 벚꽃 축제가 열린다고 하니 많은 분들이 찾아오실 것 같습니다. |
*Although OpenAI currently does not support voice cloning functionality, we still wish to conduct comparative listening tests with its excellent naturalness as a reference.
Flow-VAE vs. VAE Comparison
Flow-VAE is less likely to produce the following instabilities.
| Source Audio | Flow-VAE | VAE | Differences |
|---|---|---|---|
|
Flow-VAE reproduces more continuous and natural reverberation |
|||
|
VAE introduces unwanted high-frequency components |
|||
|
VAE produces electronic-sounding artifacts at the beginning |
Professional Voice Clone (PVC) Demonstrations
For more complex dialectal accents and tonal characteristics, PVC can reproduce these features while maintaining high naturalness based on the text content.
| Source Audio | Zero-Shot | PVC | Differences |
|---|---|---|---|
|
Like the ZeroShot version, the PVC version has rising sentence-final intonation, but distinctively sustains this elevated pitch instead of the typical pitch declination found in common declarative sentences |
|||
|
With more materials, the model not only reproduces the speaker's voice characteristics but also accurately captures more dialectal features |
Emotion Control Demonstrations
Source Audio for Refreshing Young Man
DEMO
| Neutral | Emotion | Text | Emotion Control Audio |
|---|---|---|---|
| Surprised |
天哪！我完全没想到会在这里遇见你， 都过去这么多年了，你一点都没变！ |
||
| Disgusted |
这个地方实在太脏乱了，到处都是垃圾和难闻的气味儿， 我一秒钟都不想多待。 |
||
| Fearful |
深夜回家的路上，我清楚地听见身后有脚步声在跟着我， 可是回头却什么都看不见。 |
||
| Angry |
我付出了这么多，换来的却是这样的背叛！ 你怎么可以这样对待我的信任！ |
||
| Sad |
躺在床上翻来覆去，心里压着说不出的难过和沮丧， 昨天晚上又失眠了。 |
||
| Happy |
和好朋友一起在院子里烧烤，聊着有趣的故事， 享受着美食和欢乐的时光。 |
Text-Prompted Voice Generation Demonstrations
| Prompt | Text | Audio |
|---|---|---|
|
男性中年声音，说中文，音色浑厚醇厚，带有自然的磁性， 语速偏慢，音量适中，音调偏低沉。声音整体给人沉稳可靠的感觉， 在深度访谈场景中表现出专业性和亲和力，音质清晰，吐字规整有力。 |
在这个安静的夜晚，让我们一起走进《人生笔记》这本书。 作者用平实的文字记录下生活中的点点滴滴， 让我们看到平凡中的真善美。 今天，我们先来读第一章：'生活的痕迹'...... |
|
|
说中文的女青年，音色偏甜美，语速比较快， 说话时带着一种轻快的感觉，整体音调较高，像是在直播带货， 整体氛围比较活跃，声音清晰，听起来很有亲和力。 |
亲爱的宝宝们，等了好久的神仙面霜终于到货啦！ 你们看这个包装是不是超级精致？ 我自己已经用了一个月了，效果真的绝绝子！ 而且这次活动价真的太划算了，错过真的会后悔的哦～ |
|
|
中国男性声音，听着像是青年，音色清亮，语速比较快， 说话很有激情，像是在解说比赛，声音中带着紧张和兴奋的感觉。 |
漂亮！这个进攻太精彩了！张伟突破防线， 一个漂亮的转身，球传到禁区，王超跟上，射门！ 球进了！难以置信的精彩配合，现场观众都沸腾了！ |
|
|
中国女青年的声音，音色清脆，说话速度偏快，语调活泼， 像是在做游戏直播，声音中带着愉快的感觉，整体音调较高， 整体氛围比较轻松。 |
啊！这里有个宝箱！让我们看看里面是什么～ 哇！是传说中的紫色装备！运气也太好了吧！ 谢谢小伙伴们的打赏，我们继续往前探索...... |
|
|
English-speaking female voice, sounding relatively young, with a sweet and pleasant tone. Speaking at a moderate pace with a touch of energy, similar to someone narrating a beauty/makeup tutorial video. The overall atmosphere is relaxed and cheerful. |
Hi everyone! Today I'll be sharing a soft, romantic makeup look that's perfect for dates. Many of you have been asking how to apply this eyeshadow naturally - the key is using gentle techniques. Let's go through the steps together... |
|
|
English-speaking middle-aged male voice, slightly husky, speaking at a moderate-to-slow pace with a deep tone. Like someone telling an old story, conveying a nostalgic feeling, with a relaxed and composed manner of speaking. |
That was back in the late 1970s. I remember when our village first got electricity - everyone was so excited. In theevenings, people would bring their stools and gather under the big banyan tree by the village committee office to watch movies projected on the wall. Even now, thinking back to those moments still fills me with warmth. |
Comparison of voice naturalness with the previous generation products
The new model demonstrates significant advantages in naturalness compared to the previous version.
Source Audio for Radiant_Girl
DEMO
| Text | MiniMax Speech_02_HD |
Microsoft Azure TTS |
AWS Polly |
|---|---|---|---|
|
I sat alone in the empty room, staring at the old photographs, wondering how everything could change so quickly, how a lifetime of memories could fade away just like that. |
|||
|
The moment I held my acceptance letter, my heart burst with joy - all those sleepless nights finally paid off, and I couldn't stop dancing around the room, calling everyone I knew to share this amazing news! |