Best AI Models for ElevenLabs

ElevenLabs has unveiled Scribe, a cutting-edge Automatic Speech Recognition (ASR) model that aims to provide remarkably accurate transcriptions in 99 different languages. This innovative system is tailored to effectively manage a wide range of real-world audio situations, featuring capabilities such as word-level timestamps, speaker identification, and audio-event tagging. In benchmark evaluations like FLEURS and Common Voice, Scribe has outperformed leading models, including Gemini 2.0 Flash, Whisper Large V3, and Deepgram Nova-3, achieving impressive word error rates of 98.7% for Italian and 96.7% for English. Additionally, Scribe shows a significant reduction in errors for languages that have often faced challenges, such as Serbian, Cantonese, and Malayalam, where competing models frequently report error rates above 40%. Furthermore, developers can easily incorporate Scribe into their applications via ElevenLabs' speech-to-text API, which returns structured JSON transcripts enriched with comprehensive annotations. This level of accessibility and performance is set to revolutionize the field of transcription and enhance the user experience across various applications.

Liquid AI's LFM2.5 represents an advanced iteration of on-device AI foundation models, engineered to provide high-efficiency and performance for AI inference on edge devices like smartphones, laptops, vehicles, IoT systems, and embedded hardware without the need for cloud computing resources. This new version builds upon the earlier LFM2 framework by greatly enhancing the scale of pretraining and the stages of reinforcement learning, resulting in a suite of hybrid models that boast around 1.2 billion parameters while effectively balancing instruction adherence, reasoning skills, and multimodal functionalities for practical applications. The LFM2.5 series comprises various models including Base (for fine-tuning and personalization), Instruct (designed for general-purpose instruction), Japanese-optimized, Vision-Language, and Audio-Language variants, all meticulously crafted for rapid on-device inference even with stringent memory limitations. These models are also made available as open-weight options, facilitating deployment through platforms such as llama.cpp, MLX, vLLM, and ONNX, thus ensuring versatility for developers. With these enhancements, LFM2.5 positions itself as a robust solution for diverse AI-driven tasks in real-world environments.

Mercury Edit 2 is a cutting-edge AI model from Inception Labs, part of the Mercury suite, specifically crafted for rapid reasoning, coding, and editing by employing a novel architecture distinctly different from typical large language models. It enhances the capabilities of Mercury 2, a diffusion-based model that generates and refines complete outputs simultaneously, rather than the conventional method of creating text one token at a time, which results in markedly improved speeds and more agile editing processes. Rather than functioning as a linear “typewriter,” this system operates as a dynamic editor, beginning with a rough draft and methodically enhancing it across multiple tokens simultaneously, facilitating real-time engagement and swift iterations in various tasks such as code editing, content creation, and agent-based workflows. This innovative framework achieves an impressive throughput of up to approximately 1,000 tokens per second, significantly outpacing traditional models while still upholding competitive reasoning abilities across various benchmarks. Its unique design not only transforms the way users interact with AI but also sets a new standard for performance in the field of artificial intelligence.