Anthropic's Sonnet 4.6 is now on Celeste. await celeste.text.generate(model="claude-sonnet-4-6") Model Card: https://lnkd.in/eBSKdG2x
Celeste AI
Software Development
Open source, type-safe primitives for multi-modal AI. All capabilities, all providers, one interface
About us
Open source, type-safe primitives for multi-modal AI. All capabilities, all providers, one interface. At Celeste, we provide the foundation layer for building AI applications—primitives, not frameworks. For engineers who need control over their architecture. • Unified interface for text, image, video, and much more • Provider-agnostic abstractions—switch providers with one parameter, zero code changes • Type-safe responses with full IDE autocomplete • Automatic parameter mapping and validation • Minimal overhead No vendor lock-in. Upgrade to any new model on day one. Future-proof your AI applications. You own the architecture. We provide the primitives. Learn more: github.com/withceleste/celeste-python | withceleste.ai
- Website
-
https://withceleste.ai
External link for Celeste AI
- Industry
- Software Development
- Company size
- 1 employee
- Type
- Nonprofit
Employees at Celeste AI
Updates
-
Google DeepMind's Gemini 3.1 is now available on Celeste. await celeste.text.generate(model="gemini-3.1-pro-preview") Model Card: https://lnkd.in/eMPKbvC7
-
-
Seedream 5 from BytePlus is now available on Celeste. await celeste.images.generate(model="seedream-5-0-260128") Model Card: https://lnkd.in/ei5iHcz2
-
-
Celeste AI reposted this
Release Notes February 2026: New TTS & STT Models, Pronunciation Dictionaries & AWS Integration We're excited to announce major updates to the Gradium API and Gradium Studio, delivering enhanced text-to-speech (TTS) and speech-to-text (STT) capabilities for developers and enterprises. 🎙️ Advanced TTS and STT Models Experience our latest text-to-speech model and speech recognition model with improved audio quality, accuracy, and natural-sounding voice generation. Perfect for voice applications, transcription services, and conversational AI. 📖 Custom Pronunciation Dictionaries Take control of speech synthesis with pronunciation dictionaries. Ensure brand names, technical terminology, and industry-specific acronyms are pronounced correctly every time. Ideal for healthcare, finance, and industry specific applications. ⚡ WebSocket Multiplexing for Real-Time Audio Boost performance with multiplexing support: process multiple TTS or STT requests simultaneously over a single WebSocket connection. Reduce latency, minimize connection overhead, and scale efficiently for high-volume applications. 🎁 Gradium Referral Program Love Gradium? Join our referral program: share Gradium with your network and earn up to 9M API credits while your referrals get exclusive discounts. Win-win for developers and businesses alike. ☁️ AWS Marketplace & SageMaker AI Deployment Deploy Gradium TTS and ASR models directly on AWS SageMaker with full bidirectional streaming support. Accelerate your deployment timeline while keeping your voice AI infrastructure secure within your private cloud network. Now available on AWS Marketplace. Explore the full updates in Gradium Studio and our API documentation.
-
Celeste AI reposted this
Celeste AI au Festival de Cannes 🎬 La semaine dernière, nous étions au WAICF - World AI Cannes Festival pour représenter l'IA open source. L'occasion d'échanger avec un écosystème plus business que celui auquel on est habitué. À l'ère où tout évolue si vite, il est vital pour les entreprises d'être agiles et de savoir s'adapter aux nouveaux modèles, aux nouvelles réglementations, aux changements de prix et aux nouvelles features. Pendant ces deux jours, on a pu sensibiliser mais aussi valider le besoin de pouvoir switcher de modèle sans changer son code, peu importe le provider, peu importe la modalité. Et c'est exactement le problème que Celeste résout. On a aussi fait de belles rencontres et c'est surtout ça qu'on retiendra ! 🙌 Zainab Chouiref, Bastien V., Geoffrey Harrazi, Anas Tribak, Yannick Léo, Florian Barbaro, PhD, Hadrien PEYRON, Mélaine CEYLAND, Elvis Agah, Ariel Cohen Codar, Benjamin Perroud
-
-
Celeste AI reposted this
Clap de fin pour le WAICF - World AI Cannes Festival ! C'était intense de voir autant d'acteurs réunis au même endroit. Au milieu de tout ça, j'ai eu un échange super intéressant avec l'équipe Celeste AI. Ils proposent une couche d'abstraction via un SDK Python Open Source conçu pour l'IA multimodale. En gros, ça permet d'interfacer de la vidéo, de l'audio et de l'image via une API unique, sans se coupler fortement à un fournisseur spécifique. Merci pour les discussions de qualité, ça fait du bien de sortir des écrans ! 😁
-
-
-
-
-
+4
-
-
🇫🇷 Celeste AI at WAICF - World AI Cannes Festival Come meet the team, talk open source, and discuss your multimodal AI workflows. 📍 Find us in the stand L03K #OpenSource #Multimodal #AI #Python #Cannes
-
-
Anthropic's Claude Opus 4.6 is now on Celeste. await celeste.text.generate(model="claude-opus-4-6") Model Card: https://lnkd.in/eSax7A9D
-
-
Celeste AI reposted this
Celeste AI and Claude Code meet in Paris 🌟🤖🇫🇷 Last night I talked about Multi modal AI to a room full of Claude Code users. I showcased how Celeste empowers developers to build multimodal AI pipelines with a single open source SDK. Excited to participate in more events like this one ! Thanking Olivier Legris for inviting me and the team at Dust for hosting. Shoutout to the other speakers, Henry Fontanier, Benoit Vinceneux, Laurynas Keturakis, Paul Luong, who are building really cool stuff ! credits to Joséphine Parquet for the comics 📸
-
-
Celeste AI at FOSDEM'26 🇧🇪 Our team will be in Brussels this weekend for FOSDEM. We'll be speaking at the AI Plumbers fringe (un)conference hosted by AIFoundry.org. Topic: "Primitives Over Frameworks: Building Provider-Agnostic AI Without Vendor Lock-In" Interested about the technical details behind our library ?👇 🔗 Register here: https://luma.com/3nc5qaje #FOSDEM #OpenSource #AI #CelesteAI #Python