Choose a model for voice conversation, audio and video analysis, content moderation, voice translation, and other omni-modal tasks.
Migrate from closed-source models
Map your current GPT or Gemini omni-modal/real-time capabilities to an equivalent Bailian model.
Closed-source examples | Bailian recommendation | |
|---|---|---|
Audio/video understanding and text generation | ||
Real-time translation |
|
Use cases
Omni-modal models understand text, audio, images, and video. Qwen3.8-Omni-Flash supports audio/video analysis, meeting summaries, and subtitle generation, with thinking mode, tool calling, and web search. Choose a model for your use case:
Use case | Recommended model | User guide |
|---|---|---|
Audio/video understanding and text generation: Analyze audio/video content and generate meeting summaries, subtitles, and text answers | Qwen3.8-Omni-Flash | |
Real-time voice/video conversation: Interact with AI through a microphone and camera (voice assistants, customer service bots, visual Q&A, live-stream analysis) | Qwen3.8-Omni-Flash-Realtime | |
Offline audio output: Upload audio or video files and generate speech responses | Qwen3.5-Omni | |
Real-time voice translation: Simultaneous interpretation with latency as low as 2.3 seconds, supporting 60 languages (live interpretation, multilingual meetings) | Qwen3.8-LiveTranslate-Flash-Realtime | |
Audio and video file translation: Upload audio or video files and translate them into a target language (video dubbing, podcast translation) | Qwen3-Livetranslate | |
Voice cloning: Provide a reference audio clip and the AI generates speech responses in that voice | Qwen3.8-Omni-Flash-Realtime; Qwen3.5-Omni Plus / Flash | |
Real-time voice conversation with semantic VAD: End-to-end voice interaction, semantic turn detection (smart_turn), non-meaningful utterances won't interrupt the conversation, supports Function Calling (voice assistants, smart customer service) | Qwen-Audio |
- Qwen3.8-Omni-Flash supports audio up to 3 hours and video up to 2 hours for content analysis.
- Qwen3.8-Omni-Flash-Realtime, Qwen3.8-Omni-Flash, Qwen3.5-Omni Plus / Flash (text output), Qwen3.5-Omni-Realtime, Qwen3-Omni-Flash, and Qwen-Audio Realtime support function calling.
- Qwen3.8-Omni-Flash-Realtime, Qwen3.8-Omni-Flash, Qwen3.5-Omni, and Qwen-Audio Realtime support web search.
Translation
For audio/video translation into text or subtitles, use Qwen3.8-Omni-Flash. For spoken translations, choose a model below based on latency and speech output requirements.
qwen3.8-livetranslate-flash-realtime (60 languages, latency as low as 2.3 seconds). For speech output with web search and terminology injection, choose Qwen3.8-Omni-Flash-Realtime for real-time conversations or Qwen3.5-Omni for file-based calls. Qwen3.8-Omni-Flash-Realtime supports the same speech output languages as Qwen3.5-Omni-Realtime. See the voice list for the languages supported by each voice.Supported languages
Supported languages
| Language | Qwen3.8 / 3.5-Livetranslate | Qwen3-Livetranslate | Qwen3.8-Omni-Flash-Realtime (speech) | Qwen3.5-Omni (speech) | Qwen3-Omni-Flash (speech) |
|---|---|---|---|---|---|
| English | Supported | Supported | Supported | Supported | Supported |
| Chinese (Mandarin) | Supported | Supported | Supported | Supported | Supported |
| Cantonese | Text-only | Supported | Supported | Supported | Supported |
| Sichuanese | Supported | Supported | Supported | Supported | Supported |
| Shanghainese | Supported | Supported | Unsupported | Unsupported | Supported |
| Beijingese | Supported | Supported | Supported | Supported | Supported |
| Tianjinese | Supported | Supported | Supported | Supported | Supported |
| Nanjingese | Unsupported | Unsupported | Supported | Supported | Supported |
| Shaanxi dialect | Unsupported | Unsupported | Supported | Supported | Supported |
| Hokkien | Unsupported | Unsupported | Supported | Supported | Supported |
| French | Supported | Supported | Supported | Supported | Supported |
| German | Supported | Supported | Supported | Supported | Supported |
| Russian | Supported | Supported | Supported | Supported | Supported |
| Italian | Supported | Supported | Supported | Supported | Supported |
| Spanish | Supported | Supported | Supported | Supported | Supported |
| Portuguese | Supported | Supported | Supported | Supported | Supported |
| Japanese | Supported | Supported | Supported | Supported | Supported |
| Korean | Supported | Supported | Supported | Supported | Supported |
| Thai | Supported | Supported Text only | Supported | Supported | Supported |
| Indonesian | Supported | Supported Text only | Supported | Supported | Unsupported |
| Vietnamese | Supported | Supported Text only | Supported | Supported | Unsupported |
| Arabic | Supported | Supported Text only | Supported | Supported | Unsupported |
| Hindi | Supported | Supported Text only | Supported | Supported | Unsupported |
| Turkish | Supported | Supported Text only | Supported | Supported | Unsupported |
| Finnish | Supported | Unsupported | Supported | Supported | Unsupported |
| Polish | Supported | Unsupported | Supported | Supported | Unsupported |
| Dutch | Supported | Unsupported | Supported | Supported | Unsupported |
| Czech | Supported | Unsupported | Supported | Supported | Unsupported |
| Urdu | Supported | Unsupported | Supported | Supported | Unsupported |
| Tagalog | Supported | Unsupported | Supported | Supported | Unsupported |
| Swedish | Supported | Unsupported | Supported | Supported | Unsupported |
| Danish | Supported | Unsupported | Supported | Supported | Unsupported |
| Hebrew | Supported | Unsupported | Supported | Supported | Unsupported |
| Icelandic | Supported | Unsupported | Supported | Supported | Unsupported |
| Malay | Supported | Unsupported | Supported | Supported | Unsupported |
| Norwegian | Supported | Unsupported | Supported | Supported | Unsupported |
| Persian | Supported | Unsupported | Supported | Supported | Unsupported |
| Greek | Text-only | Supported Text only | Unsupported | Unsupported | Unsupported |
| Afrikaans | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Asturian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Belarusian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Bulgarian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Bengali | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Bosnian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Catalan | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Cebuano | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Estonian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Galician | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Gujarati | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Croatian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Hungarian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Javanese | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Kazakh | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Kannada | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Kyrgyz | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Latvian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Macedonian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Malayalam | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Marathi | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Punjabi | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Romanian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Slovak | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Slovenian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Swahili | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Tajik | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Azerbaijani | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
| Ukrainian | Text-only | Unsupported | Unsupported | Unsupported | Unsupported |
Recommended models
Model | API | Use cases |
|---|---|---|
qwen3.8-omni-flash | Chat Completions / Responses | Audio/video understanding, text generation, thinking, function calling, web search |
qwen3.8-omni-flash-realtime | Realtime API (WebSocket / WebRTC / AOQ) | Realtime audio/video conversation, function calling, MCP, voice cloning |
qwen3.5-omni-plus / qwen3.5-omni-flash | Chat Completions | Offline speech output and voice cloning |
qwen3.8-livetranslate-flash-realtime | Realtime API (WebSocket) | Realtime translation |
qwen3-livetranslate-flash | Chat Completions | Audio/video file translation |
qwen-audio-3.1-realtime-plus / qwen-audio-3.0-realtime-plus / qwen-audio-3.0-realtime-flash | Realtime API (WebSocket) | Realtime voice conversation |
All models
Qwen3.8-Omni
qwen3.8-omni-flash is designed for audio/video understanding and content analysis, with thinking enabled by default. qwen3.8-omni-flash-realtime is designed for real-time audio/video conversations.
Model ID | API | Input | Output | Function Calling | Web search |
|---|---|---|---|---|---|
Chat Completions / Responses | Text, audio, images, video | Text only | Supported | Supported | |
Realtime API | Text, audio, images, video | Text, audio | Supported | Supported |
Qwen3.5-Omni
Non-real-time Qwen3.5-Omni supports audio up to 3 hours and video up to 1 hour.
Model ID | API | Input | Function calling | Web search | Thinking mode |
|---|---|---|---|---|---|
| Realtime API (WebSocket) | Text, audio, images, video | Supported | Supported | Unsupported |
| Realtime API (WebSocket) | Text, audio, images, video | Supported | Supported | Unsupported |
| Chat Completions | Text, audio, images, video | Supported (Beijing, text output) | Supported | Unsupported |
| Chat Completions | Text, audio, images, video | Supported (Beijing, text output) | Supported | Unsupported |
| Realtime API (WebSocket) | Text, audio, images, video | Supported | Supported | Unsupported |
| Realtime API (WebSocket) | Text, audio, images, video | Supported | Supported | Unsupported |
| Chat Completions | Text, audio, images, video | Supported (Beijing, text output) | Supported | Unsupported |
| Chat Completions | Text, audio, images, video | Supported (Beijing, text output) | Supported | Unsupported |
Qwen3-Omni
Model ID | API | Input | Function calling | Web search | Thinking mode |
|---|---|---|---|---|---|
| Realtime API (WebSocket) | Text, audio, images, video | Unsupported | Unsupported | Unsupported |
| Chat Completions | Text, audio, images, video | Supported | Unsupported | Supported |
Qwen3.8-Livetranslate
| Model ID | API | Input | Languages |
|---|---|---|---|
| qwen3.8-livetranslate-flash-realtime | Realtime API | Audio, images | 60 |
Qwen3.5-Livetranslate
Model ID | API | Input | Languages |
|---|---|---|---|
| Realtime API (WebSocket) | Audio, images | 60 |
| Realtime API (WebSocket) | Audio, images | 60 |
Qwen3-Livetranslate
Model ID | API | Input | Languages |
|---|---|---|---|
| Chat Completions | Audio, video | 18 |
| Chat Completions | Audio, video | 18 |
Qwen-Audio
Model ID | API | Input | Function calling | Web search | Thinking mode |
|---|---|---|---|---|---|
| Realtime API (WebSocket) | Audio, text | Supported | Supported | Unsupported |
| Realtime API (WebSocket) | Audio, text | Supported | Supported | Unsupported |
| Realtime API (WebSocket) | Audio, text | Supported | Supported | Unsupported |