LIVETracking 976 AI models from 268 providers.
Beta
Home/Models/Higgs Audio V2 Generation 3B Base
BA

Higgs Audio V2 Generation 3B Base

by Boson AI · Released Jul 2025

Compare
Context
N/A
Input $/1M
TBD
Output $/1M
TBD
Type
text-to-speech
License
Proprietary
Benchmarks
0 tested
Data updated today
About

Bosonai text to speech model. 621K downloads on HuggingFace.

No benchmark data available yet.

Similar Models
OpenAI logo
GPT-5.4 Image 2
OpenAI
0.0$8.00/1M
Mistral AI logo
Mistral Small 3.2 24B
Mistral AI
0.0$0.07/1M
Alibaba Qwen logo
Qwen VL Max
Alibaba Qwen
0.0$0.52/1M
Links
Info
Boson AI
Research
Technical Report
Documentation
API DocsPlayground
Community
@Boson AI
BenchGecko API
bosonai-higgs-audio-v2-generation-3b-base
Specifications
  • Typetext-to-speech
  • ContextN/A
  • ReleasedJul 2025
  • LicenseProprietary
  • StatusActive
Available On
BA
Boson AITBD
Learn More
transformertokens
Share & Export
Tweet
Related Models
OpenAI logoGPT-5.4 Image 2
0.0
Mistral AI logoMistral Small 3.2 24B
0.0
Alibaba Qwen logoQwen VL Max
0.0
openrouter logoElephant
0.0
Higgs Audio V2 Generation 3B Base is a proprietary text-to-speech AI model by Boson AI, released in July 2025.

Related Models

GPT-5.4 Image 2 · OpenAIMistral Small 3.2 24B · Mistral AIQwen VL Max · Alibaba QwenElephant · openrouterGPT-4o Audio · OpenAI

Benchmarks

Related Pages

Boson AI · ProviderAll ModelsCompare Models