Darwin-TTS-1.7B-Cross
World's first cross-modal FFN transfer from LLM to TTS — emotion-enhanced speech synthesis without any training.
text → audio · made by FINAL_Bench
Sold by
Nobody in the catalogue publishes a price for this yet.
About
Darwin-TTS-1.7B-Cross — an audio model from FINAL_Bench.
It takes text and returns audio. It was published in April 2026. The catalogue files it under speak. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- FINAL_Bench
- Register
- model
- Takes
- text
- Returns
- audio
- Published
- April 2026
- Parameters
- 1.7 billion · read from its own name
- Licence
- apache-2.0
Known as 1 name
FINAL-Bench/Darwin-TTS-1.7B-Cross