bosonai / text-to-speech updated 1 month ago

higgs-tts-2-3b-base

Check our open-source repository https://github.com/boson-ai/higgs-audio for more details!

Params
5.8 B
Context
2,048
Downloads 30d
368 K
Likes
694
Licence: other Not gated SAFETENSORS 4 languages View on Hugging Face ↗

Download history

tracking started — chart appears after 7 days of snapshots (1 recorded)
368 K downloads in the last 30 days

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 11.5 GB 14.1 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture
HiggsAudioV2ForConditionalGeneration
Parameters
5.8 B
Tensor type
BF16
Context length
2,048
Vocabulary
128,256
Layers / heads
28 / 24
Licence
other
First seen on the Hub
2025-07-01
Training datasets
undisclosed
Added to our catalog
2026-08-07