@@ -28,9 +28,11 @@ <h4 style="font-size: 1.3rem; line-height: 1; text-align: center;">Intrinsic Zer
28
28
Encoder</ h4 >
29
29
< p class ="author ">
30
30
MiniMax Team < span class ="date "> May 2025</ span > < br />
31
- < a style ="font-size: 1.1rem; " target ="_blank "
32
- href ="https://minimax-ai.github.io/tts_tech_report/MiniMax_Speech.pdf "> [Tech
31
+ < a style ="font-size: 1.1rem; " target ="_blank " href ="https://arxiv.org/abs/2505.07916 "> [Tech
33
32
Report]</ a >
33
+ < a style ="font-size: 1.1rem; margin-left: 1rem; " target ="_blank "
34
+ href ="https://huggingface.co/datasets/MiniMaxAI/TTS-Multilingual-Test-Set "> [Multilingual Test Set]</ a >
35
+ < a style ="font-size: 1.1rem; margin-left: 1rem; " target ="_blank " href ="https://github.com/MiniMax-AI "> [GitHub]</ a >
34
36
</ p >
35
37
</ header >
36
38
@@ -57,13 +59,16 @@ <h2>Abstract</h2>
57
59
control
58
60
via LoRA; text to voice (T2V) by synthesizing timbre features directly from text description; and professional
59
61
voice
60
- cloning (PVC) by fine-tuning timbre features with additional data. Welcome to visit
61
- < a href ="https://www.minimax.io/audio "> MiniMax Audio</ a > and
62
- explore our powerful TTS features.
62
+ cloning (PVC) by fine-tuning timbre features with additional data.
63
63
</ p >
64
64
</ div >
65
65
66
66
< nav role ="navigation " class ="toc ">
67
+ < h2 > Explore MiniMax-Speech</ h2 >
68
+ < p > Welcome to visit
69
+ < a href ="https://www.minimax.io/audio "> MiniMax Audio</ a > and
70
+ explore our powerful TTS features.
71
+ </ p >
67
72
< h2 > Contents</ h2 >
68
73
< ol >
69
74
< li >
@@ -232,9 +237,8 @@ <h2 id="zero-shot-vs-one-shot-demonstrations">Zero-Shot vs. One-Shot Demonstrati
232
237
features based
233
238
on the text content, whereas OneShot adheres more strictly to the speaker characteristics (prosody, speech
234
239
rate,
235
- emotions, etc.) demonstrated in the audio prompt (The additional input that OneShot has compared to ZeroShot,
236
- see
237
- technical report for details).
240
+ emotions, etc.). For details of Zero-Shot and One-Shot, refer to the < a
241
+ href ="https://arxiv.org/abs/2505.07916 " target ="_blank "> technical report</ a > .
238
242
</ p >
239
243
< div class ="scroll-wrapper " style ="margin-top: 2rem; ">
240
244
< table style ="width: 100%; ">
0 commit comments