BASE MODEL · TTS

Fish Speech 1.5

Multilingual TTS with LoRA fine-tuning support.

Voices built on Fish Speech 1.5

Technical details

Architecture
Dual autoregressive transformer + VQ-GAN
Type
TTS
Size
1.3 GB
Runs on
~4 GB VRAM
Languages
English, Chinese, Japanese, Korean, French, German, Spanish and more
Recommended settings
temperature=0.7 · top_p=0.7 · repetition_penalty=1.2
Version
1.5 · updated 5 mo ago
Source
Hugging Face
License
CC-BY-NC-SA-4.0 · Non-commercial

Fish Speech 1.5 is developed and owned by its original authors. timbre only indexes it.

COMPARE Compare