此语言仍有 24 条内容或界面任务待翻译;未完成部分显示中文原文。
AI Home / Model Library / qwen3-livetranslate-flash

qwen3-livetranslate-flash

AI 辅助整理
阿里云百炼非实时音视频翻译音频输入Video Input文本输出音频输出语种自动识别流式输出Enter Reference Price · Official Prices Prevail

qwen3-livetranslate-flash is a non-real-time audio/video translation model on the Alibaba Cloud Bailian platform, invoked via an OpenAI-compatible interface. It supports audio and video file input and outputs translated text; it can also output audio simultaneously under the ["text","audio"] modality (wav format only). The interface supports only a single User Message and streaming output. Translation languages are specified via translation_options, and the source language can be auto-detected if not set. It is suitable for offline translation of recorded audio/video content and not suitable for workflows that require the DashScope interface or non-streaming calls.

Context tokensPending Verification
Input / Million tokensPending Verification
Output / Million tokensPending Verification
Versionqwen3-livetranslate-flash-2025-12-01
Deployment云端 API,通过 OpenAI 兼容接口调用;北京与新加坡地域业务空间专属域名,需配置 API Key;不支持通过 DashScope 接口调用,仅支持流式输出(stream 仅可设为 true)

Capabilities & Use Cases

非实时音视频翻译音频输入Video Input文本输出音频输出语种自动识别流式输出

Interface & Deployment: The model is invoked via an OpenAI-compatible interface. The base_url is https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1 for the Beijing region and https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1 for the Singapore region; {WorkspaceId} is the workspace ID. The original documentation explicitly states that "invocation via the DashScope interface is not supported" and that "the model only supports streaming output calls; it can only be set to true". Input & Output: For audio input, type is input_audio (data supports a URL or Base64, with formats such as mp3, wav); for video input, type is video_url (public URL or Base64 Data URL). The output modalities parameter can be ["text"] or ["text","audio"]; when outputting audio, voice and format must be configured, and format only supports wav. The message array supports only one User Message. Translation & Sampling Parameters: translation_options is required; target_lang is mandatory, while source_lang is optional (auto-detected if not set). To ensure translation accuracy, the documentation does not recommend modifying sampling parameters such as temperature, top_p, presence_penalty, top_k, and repetition_penalty; speech_rate can control output speech rate within 0.5–2.0. top_k and repetition_penalty are non-OpenAI-standard parameters and must be placed in extra_body in the Python SDK. Versions & Metering: Supported models are qwen3-livetranslate-flash and qwen3-livetranslate-flash-2025-12-01. Token usage is calculated based on prompt_tokens and completion_tokens. Tokens for input audio and video are counted separately in prompt_tokens_details.audio_tokens; audio tokens in video files are also counted in this field, and input text tokens are fixed at 0. Integration Notes: The API keys differ between the Beijing and Singapore regions; the default and maximum values of max_tokens are both the model's maximum output length, and output exceeding it will be truncated. Before selection, consult the official "Supported Voices," "Supported Languages," and "Model Selection" documentation to confirm specific capability boundaries.

Capability Comparison

No verified item-by-item scores available; capability radar and overall ranking will not be displayed for now.

Data & Sources

Data Provider
阿里云百炼
On-site profile update
2026-11-05 01:42:27

On-site update time is not equivalent to the model release date. Official or platform benchmark scores are not displayed when test sets, dates, or original results are not provided.

Version History

qwen3-livetranslate-flash-2025-12-01Current Entry Version

Historical versions, release and discontinuation dates to be verified.

Access & Usage

Please confirm the API address, model identifier, authentication, permissions, and billing rules according to the official documentation.

Open Official Documentation

Platform Tested

No verified model test reports available. Model capability tags do not indicate completed platform testing.
Product Selection Assistant

让需求变成可修改的筛选条件

依据已录入参数生成条件,结果可查看和修改。帧率与性能需核对实测,不能仅凭算力数值保证。