LTX builds open world models, AI systems that generate, simulate, and shape video, audio, and the physical world. Lightricks created LTX so that developers, studios, and enterprises can own the model they build on, not just rent access to someone else's.
The current release, LTX-2.5, is a 22B-parameter dual-stream diffusion transformer. It renders native 4K footage at up to 50fps and produces synchronized audio and video in one pass, no separate tools required. Independent benchmarks from Artificial Analysis place LTX in the top three AI video models worldwide.
There is no single way to work with LTX. Pull the open weights and run the model yourself on your own machines. Take a commercial license for on-premise deployment with full enterprise support. Or use LTX Studio, the packaged production suite for creative teams that want the model without managing the infrastructure. ElevenLabs, Asteria Film Co., Magnopus, and NVIDIA all build on it today.
If you need a quick clip for social media, look elsewhere. LTX exists for AI teams turning video, audio, and simulation into part of their own product, not a novelty.
Learn more
Google AI Studio is a comprehensive platform for discovering, building, and operating AI-powered applications at scale. It unifies Google’s leading AI models, including Gemini, Imagen, Veo, and Gemma, in a single workspace. Developers can test and refine prompts across text, image, audio, and video without switching tools. The platform is built around vibe coding, allowing users to create applications by simply describing their intent. Natural language inputs are transformed into functional AI apps with built-in features. Integrated deployment tools enable fast publishing with minimal configuration. Google AI Studio also provides centralized management for API keys, usage, and billing. Detailed analytics and logs offer visibility into performance and resource consumption. SDKs and APIs support seamless integration into existing systems. Extensive documentation accelerates learning and adoption. The platform is optimized for speed, scalability, and experimentation. Google AI Studio serves as a complete hub for vibe coding–driven AI development.
Learn more
Orate
Orate is an advanced AI toolkit specifically crafted for speech applications, enabling developers to produce realistic, human-like audio and transcribe spoken language seamlessly through a unified API that is compatible with prominent AI platforms such as OpenAI, ElevenLabs, and AssemblyAI. This innovative platform includes text-to-speech features, which allow users to convert written text into authentic audio effortlessly via an intuitive API that integrates with various service providers. For instance, developers can simply generate speech from text prompts by utilizing the 'speak' function from Orate in tandem with their chosen provider. In addition, Orate demonstrates exceptional proficiency in speech-to-text conversion, transforming spoken words into precise and coherent text quickly and reliably. Users can leverage the 'transcribe' function along with their desired provider to convert audio files into written material with ease. The toolkit also boasts capabilities for speech-to-speech conversion, enabling users to alter the voice in their audio using a simple voice-to-voice API that works seamlessly with top AI services, thus providing a flexible solution for diverse audio processing requirements. With its extensive array of features, Orate is a standout resource for anyone aiming to elevate their audio applications, making it a must-have for developers in the field. Moreover, its adaptability ensures that it can cater to a wide range of use cases, from content creation to accessibility solutions.
Learn more
Scribe
ElevenLabs has introduced Scribe, an advanced Automatic Speech Recognition (ASR) model designed to deliver highly accurate transcriptions in a remarkable 99 languages. This pioneering system is specifically engineered to adeptly handle a diverse array of real-world audio scenarios, incorporating features like word-level timestamps, speaker identification, and audio-event tagging. In benchmark tests such as FLEURS and Common Voice, Scribe has surpassed top competitors, including Gemini 2.0 Flash, Whisper Large V3, and Deepgram Nova-3, achieving outstanding word error rates of 98.7% for Italian and 96.7% for English. Moreover, Scribe significantly minimizes errors for languages that have historically presented difficulties, such as Serbian, Cantonese, and Malayalam, where rival models often report error rates exceeding 40%. The ease of integration is also noteworthy, as developers can seamlessly add Scribe to their applications through ElevenLabs' speech-to-text API, which delivers structured JSON transcripts complete with detailed annotations. This combination of accessibility, performance, and adaptability promises to transform the transcription landscape and significantly improve user experiences across a multitude of applications. As a result, Scribe’s introduction could lead to a new era of efficiency and precision in speech recognition technology.
Learn more
