Boson AI Headlines

Digg

A roundup of open-weight model releases includes Boson AI's Higgs Audio v3 TTS model among 25+ models, highlighting its features.

Companies:Boson AI

Digg

Boson AI released Higgs Audio v3, a 4B-parameter TTS model with low-latency streaming, zero-shot voice cloning, and support for 100 languages.

Companies:Boson AI

Digg

Boson AI released Higgs Audio v3, a 4B-parameter TTS model supporting zero-shot voice cloning across 100 languages with streaming capabilities.

Companies:Boson AI

Digg

Boson AI released Higgs Audio v3 TTS model with SGLang-Omni integration, processing 14.74 requests per second on an H100.

Companies:Boson AI

Boson AI Blog

Boson AI announced the launch of its Higgs-Audio v3 Speech-To-Text Model, representing a significant update to their audio understanding technology.

Companies:Boson AI

Boson AI Blog

Boson AI open-sourced Higgs Audio V2, a powerful audio foundation model pretrained on over 10 million hours of audio data. The model supports text-to-speech (TTS) and automatic speech recognition (ASR) with innovative features including automatic rhythm adaptation, multi-speaker dialog capabilities, and voice cloning. The release marked a significant expansion from Boson AI's earlier LLM work into audio AI.

Companies:Boson AI