Most AI video tools hand you a black box: closed weights, a subscription, and no way to see what is happening under the hood. LTX takes the opposite approach. Built by Lightricks, LTX is an open foundation model that generates and simulates across video, audio, and the physical world, and it puts the weights, the code, and the control in your hands.
At the center of the model is LTX-2.5, a 22B-parameter dual-stream diffusion transformer that produces native 4K video at up to 50 frames per second, with audio and video generated together in a single pass rather than stitched together afterward. Artificial Analysis, an independent benchmarking group, currently ranks LTX among the top three AI video models in the world.
You choose how you want to use it. Download the open weights and run LTX-2.5 on your own hardware. License the model for on-premise deployment backed by enterprise support. Or build directly on LTX Studio, the production suite that turns the model into a full creative workflow. Companies like ElevenLabs, Asteria Film Co., Magnopus, and NVIDIA already rely on LTX for their own work.
LTX is not built for one-off social clips. It is infrastructure for teams that generate motion, audio, and physical environments as part of their own products and pipelines.
Learn more
An API powered by Google's AI technology allows you to accurately convert speech into text. You can accurately caption your content, provide a better user experience with products using voice commands, and gain insight from customer interactions to improve your service. Google's deep learning neural network algorithms are the most advanced in automatic speech recognition (ASR). Speech-to-Text allows for experimentation, creation, management, and customization of custom resources. You can deploy speech recognition wherever you need it, whether it's in the cloud using the API or on-premises using Speech-to-Text O-Prem. You can customize speech recognition to translate domain-specific terms or rare words. Automated conversion of spoken numbers into addresses, years and currencies. Our user interface makes it easy to experiment with your speech audio.
Learn more
Simba 3.2
Speechify provides a range of Simba models within its text-to-speech API, designed for real-time voice generation in English and various European languages, as well as for a wide array of multilingual applications. For new English integrations, Simba 3.2 is the recommended choice, featuring streaming-native synthesis, minimized time to first byte, enhanced expressivity compared to prior versions, and comprehensive support for SSML and emotional modulation. Meanwhile, Simba 3.0 offers streaming-native speech capabilities in English, German, Spanish, French, Italian, and Brazilian Portuguese, with language selection managed via the request or voice locale. Simba Multilingual expands support to 35 locales across 30 languages, accommodating mixed-language content and incorporating automatic language detection, while the legacy Simba English model remains available for those requiring compatibility. Developers can easily select their preferred model using a single parameter, allowing for seamless switching without altering other request components, such as voice, format, and SSML configurations. This flexibility ensures that developers can optimize their integration to best meet their specific needs.
Learn more
Qwen3-TTS
Qwen3-TTS represents an innovative collection of advanced text-to-speech models created by the Qwen team at Alibaba Cloud, released under the Apache-2.0 license, which delivers stable, expressive, and real-time speech output with functionalities like voice cloning, voice design, and precise control over prosody and acoustic features. This suite supports ten prominent languages—Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian—along with various dialect-specific voice profiles, enabling adaptive management of tone, speech rate, and emotional delivery tailored to text semantics and user instructions. The architecture of Qwen3-TTS incorporates efficient tokenization and a dual-track design, facilitating ultra-low-latency streaming synthesis, with the first audio packet generated in approximately 97 milliseconds, making it ideal for interactive and real-time applications. Additionally, the range of models available offers diverse capabilities, such as rapid three-second voice cloning, customization of voice timbres, and voice design based on given instructions, ensuring versatility for users in many different scenarios. This flexibility in design and performance highlights the model's potential for a wide array of applications in both commercial and personal contexts.
Learn more
