MODEL DIRECTORY

Latest AI models

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

Newest first7 languages
Clear

6 models

Newest first
Alibaba

Qwen-Audio-3.1-ASR-Flash-Filetrans

Qwen-Audio-3.1-ASR-Flash-Filetrans is an end-to-end, non-real-time speech recognition model for transcribing recorded audio and video. Alibaba Cloud lists it under September 21, 2026 in its…

Alibaba

Qwen-Audio-3.1-ASR-Flash

Qwen-Audio-3.1-ASR-Flash is a speech-recognition model designed for efficient transcription of short audio, including multilingual and cultural content. It accepts audio and outputs text. Alibaba’s…

Alibaba

Qwen-Audio-3.1-ASR-Flash-Streaming

Qwen-Audio-3.1-ASR-Flash-Streaming is an end-to-end, real-time automatic speech recognition model. It accepts audio and produces text, returning intermediate and final transcription results as speech…

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…