Hugging Face's logo

kyutai
/
tts-1.6b-en_fr

Text-to-Speech
Moshi
English
French
tts
audio
Model card Files
xet
 Community
4
adefossez commited on
Commit
f654396
·
verified ·
1 Parent(s): 21593e7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -10,13 +10,12 @@ tags:
10
  ---
11
  # Model Card for Kyutai TTS
12
 
13
- See also the [project page](https://kyutai.org/next/tts),
 
14
  the [Colab example](https://colab.research.google.com/github/kyutai-labs/delayed-streams-modeling/blob/main/tts_pytorch.ipynb),
15
  the [GitHub repository](https://github.com/kyutai-labs/delayed-streams-modeling/),
16
  and the [repository of voices](https://huggingface.co/kyutai/tts-voices).
17
 
18
- Pre-print research paper is coming soon!
19
-
20
  This is a model for streaming text-to-speech (TTS).
21
  Unlike offline text-to-speech, where the model needs the entire text to produce the audio,
22
  our model starts to output audio as soon as the first few words from the text have been given as input.
 
10
  ---
11
  # Model Card for Kyutai TTS
12
 
13
+ See also the [pre-print research paper](https://arxiv.org/abs/2509.08753),
14
+ the [project page](https://kyutai.org/next/tts),
15
  the [Colab example](https://colab.research.google.com/github/kyutai-labs/delayed-streams-modeling/blob/main/tts_pytorch.ipynb),
16
  the [GitHub repository](https://github.com/kyutai-labs/delayed-streams-modeling/),
17
  and the [repository of voices](https://huggingface.co/kyutai/tts-voices).
18
 
 
 
19
  This is a model for streaming text-to-speech (TTS).
20
  Unlike offline text-to-speech, where the model needs the entire text to produce the audio,
21
  our model starts to output audio as soon as the first few words from the text have been given as input.