AI Model Library: LLMs, Agents & Dev Tools
Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.
Tag: Speech AI
115 article(s) found · Clear tag
Mega-ASR – NTU, NUS & Shanghai AI Lab Open-Source Speech Recognition Model
Mega-ASR is an open all-scenario robust ASR foundation from Nanyang Technological University (NTU), National University of Singapore (NUS), and Shanghai AI Lab. Built on Qwen3-ASR 1.7B, it uses compos...
MAI-Voice-2 – Microsoft's Next-Generation Text-to-Speech Model
MAI-Voice-2 is Microsoft's next-generation text-to-speech (TTS) model launched in June 2026, built on a proprietary speech foundation architecture. It delivers a generational leap in fidelity, languag...
Magenta RealTime 2 – Google's Open Real-Time Music Generation Model
Magenta RealTime 2 (MRT2) is Google Magenta's second-generation open local real-time music generation model. Built on frame-by-frame autoregressive architecture, it compresses audio generation latency...
LongCat-Video-Avatar 1.5 – Meituan's Open-Source Digital Human Video Generation Model
LongCat-Video-Avatar 1.5 is Meituan LongCat's open audio-driven digital human video framework, built on the 13.6B-parameter LongCat-Video base. Upgrading the audio encoder from Wav2Vec2 to Whisper-Lar...
Khala – Central Conservatory of Music & Tsinghua Open-Source AI Music Model
Khala is an open-source AI music foundation model jointly developed by the Central Conservatory of Music and Tsinghua University, focused on high-fidelity song generation. It uses a 64-layer deep acou...
JoyAI-Echo – JD's Open-Source Long-Form Audio-Video Generation Framework
JoyAI-Echo is an open-source long-form audio-video generation framework from JD Future Academy, designed for minute-scale multi-shot story generation. Through four technical innovations—a paired cross...
Hojo-ASR-V1 – Hojo’s Open-Source Automatic Speech Recognition Model
Hojo-ASR-V1 is an open-source automatic speech recognition model from startup Hojo. Its four-stage hybrid stack combines Whisper feature extraction, Qwen3-Omni audio encoding, Conformer adaptation, an...
Grok Imagine Video 1.5 – xAI's Image-to-Video Model
Grok Imagine Video 1.5 is xAI's next-generation image-to-video model built on the in-house Aurora autoregressive engine. Upload a single static image and a natural-language prompt to generate a short ...
Gemini 3.5 Live Translate – Google's Most Real-Time Translation Model
Gemini 3.5 Live Translate is Google's latest real-time speech translation model, built on an end-to-end streaming architecture for near-real-time speech-to-speech translation across 70+ languages. It ...
Dulus – Open-Source CLI AI Agent with Multi-Model Tool Calling
Dulus is an open-source command-line AI Agent framework of roughly 12K lines of Python, supporting 40+ mainstream language models including Claude, GPT, Gemini, DeepSeek, Kimi, and Qwen. Its core inno...
Subscribe to AI Model Reviews
Get in-depth reviews the moment a new AI model drops. Know its capabilities and use cases.
We never share your email. Unsubscribe anytime.