Text-to-Speech
vllm
mistral-common
y123456y78 commited on
Commit
8c97c06
·
verified ·
1 Parent(s): c9bf70a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -41,7 +41,7 @@ TODO:
41
  ## Key Features
42
 
43
  The Voxtral Mini 4B Realtime model offers the following capabilities:
44
- - **Text-to-Speech** generation with 5 preset voices: **casual_female**, **casual_male**, **cheerful_female**, **neutral_female**, and **neutral_male**
45
  - **Multilingual support**: English, French, Spanish, German, Italian, Portuguese, Dutch, Arabic, and Hindi
46
  - **24 kHz audio output** in WAV, PCM, FLAC, MP3, AAC, and Opus formats
47
  - **Low-latency, high-throughput inference** with batch inference and streaming output support
 
41
  ## Key Features
42
 
43
  The Voxtral Mini 4B Realtime model offers the following capabilities:
44
+ - **Text-to-Speech** generation with 20 preset voices across different languages
45
  - **Multilingual support**: English, French, Spanish, German, Italian, Portuguese, Dutch, Arabic, and Hindi
46
  - **24 kHz audio output** in WAV, PCM, FLAC, MP3, AAC, and Opus formats
47
  - **Low-latency, high-throughput inference** with batch inference and streaming output support