qwen3.5-livetranslate-flash-realtime

Realtime
Audio
Voice
Multilingual
Fast

Standard & Paid Price

Standard Price
MeterStandard Price
Input price$0.5500 / 1M tokens
Completion price$20.0000 / 1M tokens
Image input price$0.5500 / 1M tokens
Audio input price$7.5000 / 1M tokens
Audio completion price$30.0000 / 1M tokens
Billing details

Description

Alibaba Qwen3.5-LiveTranslate-Flash-Realtime — simultaneous audio and video interpretation over a WebSocket session, built on the Qwen3.5-Omni base with cross-language, cross-modal alignment and visual enhancement. Listens in 60 languages and speaks 29. Reached over GET /v1/realtime. Its price faces differ from the other realtime models: there is no text-input rate — input is billed as audio or image, and output as text or audio.

Capabilities

Input modalities
audio, image, video
Output modalities
text, audio

API endpoints

  • GET /v1/realtime (realtime)