tts-1.6b-en_fr
Released by kyutai in 2025, tts-1.6b-en_fr is a 2 billion parameter speech-and-audio model. tts-1.6b-en_fr is an open-weights audio model with roughly 2 billion parameters.
by kyutai · 2B parameters
Best for
Ways to use tts-1.6b-en_fr in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your kyutai API key. osFoundry discovers tts-1.6b-en_fr 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
tts-1.6b-en_fr 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 tts-1.6b-en_fr
tts-1.6b-en_fr runs on a single 16GB consumer GPU (~2 GB VRAM with KV-cache headroom). Full-precision inference fits on a single H100 80GB at FP16 precision (~5 GB).
tts-1.6b-en_fr vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about tts-1.6b-en_fr
Is tts-1.6b-en_fr free to use?
tts-1.6b-en_fr 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 tts-1.6b-en_fr 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 tts-1.6b-en_fr need?
Approximately 2 GB at Q4 quantisation, or 5 GB at full FP16 precision. Fits on a single 24GB consumer GPU.
Can I run tts-1.6b-en_fr locally?
Yes. tts-1.6b-en_fr is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is tts-1.6b-en_fr best at?
tts-1.6b-en_fr is well-suited to text to speech.
How do I use tts-1.6b-en_fr in osFoundry?
Paste your kyutai API key in the key dialog (or deploy the open weights for self-hostable models), assign tts-1.6b-en_fr to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by kyutai on June 30, 2025. Source: https://huggingface.co/kyutai/tts-1.6b-en_fr