MODEL DIRECTORY

Latest AI models

New releases, in one place. Explore models by their publication date.

Newest first7 languages
Clear

67 models

Newest first
Alibaba

Qwen-Audio-3.1-ASR-Flash-Message

A generative automatic speech recognition model optimized for voice messages, voice input, and enterprise use. It takes audio input and produces text, with incremental streaming transcription. Alibaba…

Alibaba

Qwen-Audio-3.1-TTS-Next

Qwen-Audio-3.1-TTS-Next is a unified audio-generation model served through Alibaba Cloud Model Studio. Unlike conventional speech-only TTS, it can generate speech, sound effects and ambient audio…

Alibaba

Qwen3.8-Omni-Flash-Realtime

Qwen3.8-Omni-Flash-Realtime is a real-time multimodal model for audio and video interaction. It accepts text, images, streaming audio and video frames, and produces text and audio. It is suited to…

Baidu

端到端语音语言大模型(Flex)

Baidu Flex is an end-to-end speech-language model for flexible, task-oriented real-time voice interactions. Its public beta was announced on September 16, 2026. (cloud.baidu.com) Understands speech…

Tencent

AuK-Flash

AuK-Flash is the distilled, four-step inference variant of AuK, Tencent’s 1.5-billion-parameter foundation model for speech generation and editing. It accepts natural-language instructions and,…

Tencent

AuK

AuK is an open-source, 1.5-billion-parameter foundation model for speech generation and editing through natural-language instructions and, where needed, reference audio. This entry describes the base…