higgs-audio-v3-8b-stt
Built by bosonai, higgs-audio-v3-8b-stt is a 8 billion parameter speech-and-audio model. higgs-audio-v3-8b-stt is an open-weights audio model with roughly 8 billion parameters.
by bosonai · 8B parameters
Best for
- automatic speech recognition
Ways to use higgs-audio-v3-8b-stt in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your bosonai API key. osFoundry discovers higgs-audio-v3-8b-stt automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
higgs-audio-v3-8b-stt is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
What hardware can run higgs-audio-v3-8b-stt
higgs-audio-v3-8b-stt runs on a single 16GB consumer GPU (~5 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~20 GB).
higgs-audio-v3-8b-stt vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about higgs-audio-v3-8b-stt
Is higgs-audio-v3-8b-stt free to use?
higgs-audio-v3-8b-stt is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use higgs-audio-v3-8b-stt commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
How much VRAM does higgs-audio-v3-8b-stt need?
Approximately 5 GB at Q4 quantisation, or 20 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run higgs-audio-v3-8b-stt locally?
Yes. higgs-audio-v3-8b-stt is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is higgs-audio-v3-8b-stt best at?
higgs-audio-v3-8b-stt is well-suited to automatic speech recognition.
How do I use higgs-audio-v3-8b-stt in osFoundry?
Paste your bosonai API key in the key dialog (or deploy the open weights for self-hostable models), assign higgs-audio-v3-8b-stt to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by bosonai on March 30, 2026. Source: https://huggingface.co/bosonai/higgs-audio-v3-8b-stt