Multilingual conversation

Updated at:

This feature provides single-language conversations for popular languages across Europe, the Americas, and Asia. Select a language when you create a multimodal application, and the system configures the most suitable speech models, prompts, and features automatically.

Supported languages

Language

Application type

Speech recognition

Speech synthesis

LLM conversation - detailed features

Chinese (Mandarin)

Multimodal application

Voice application

Supported

Supported

  • All features available

English

Supported

Supported

  • Chit-chat and knowledge Q&A

  • Web search

  • Semantic rejection and end-of-conversation detection

  • Conversational follow-ups

  • Knowledge base

  • Instructions: system instructions and custom instructions

  • Plugins: custom plugins

  • MCP services: custom MCPs

  • Agent: Bailian "My Apps", third-party applications, video calls & photo Q&A & photo translation

French, German, Spanish, Italian, Russian, Portuguese, Korean, Japanese, Thai, Indonesian, Malay

Multimodal application

Supported

(hotwords not supported)

Supported

  • Chit-chat and knowledge Q&A (web search not currently supported)

  • Instructions: system instructions and custom instructions

  • Plugins: custom plugins

  • MCP services: custom MCPs

  • Agent: Bailian "My Apps", third-party applications, video calls & photo Q&A & photo translation

Cantonese

Supported

(hotwords not supported)

Supported

Vietnamese, Filipino

Supported

(hotwords not supported)

Currently requires integration with a third-party model

Arabic, Hindi, Turkish, Ukrainian, Czech, Danish, Finnish, Icelandic, Norwegian, Polish, Dutch, Swedish

Supported

(hotwords not supported)

Currently requires integration with a third-party model

Usage notes

  • Only single-language conversations are supported; mixed-language conversations are not supported (except Chinese-English code-switching).
  • To offer multiple languages on the same hardware device, create a separate application for each language and switch the application ID through system settings to deliver the conversation capability of the corresponding language to end users.
  • Billing for the above languages follows the same logic as Chinese.

ASR and TTS model selection recommendations

  • The speech models available and recommended for each language are listed in the following table:

Language

Recommended ASR model

(performance first)

Available ASR models

Recommended TTS model & timbre

(performance first)

Available TTS models

Chinese

  • Fun-ASR Real-time Speech Recognition

  • Qwen3-ASR-Flash-Realtime

  • Fun-ASR Real-time Speech Recognition

  • Qwen3-ASR-Flash-Realtime

  • Paraformer Speech Recognition

  • Multimodal Interaction Lightweight Speech Recognition

  • CosyVoice-v3-Flash Large Model Longanhuan

  • CosyVoice-v3-Flash Large Model

  • Qwen3-TTS-Flash-Realtime

  • CosyVoice-v3-Plus Large Model

  • CosyVoice-v2 Large Model

  • Sambert Speech Synthesis Model

  • Multimodal Interaction Lightweight Speech Synthesis

English

  • Fun-ASR Real-time Speech Recognition

  • Qwen3-ASR-Flash-Realtime

  • Fun-ASR Real-time Speech Recognition

  • Qwen3-ASR-Flash-Realtime

  • Paraformer Speech Recognition (including lightweight version)

  • CosyVoice-v3-Flash Large Model Longanhuan

  • CosyVoice-v3-Flash Large Model

  • Qwen3-TTS-Flash-Realtime

  • CosyVoice-v3-Plus Large Model

  • CosyVoice-v2 Large Model

  • Sambert Speech Synthesis Model

  • Multimodal Interaction Lightweight Speech Synthesis

Japanese

  • Fun-ASR Real-time Speech Recognition

  • Qwen3-ASR-Flash-Realtime

  • Fun-ASR Real-time Speech Recognition

  • Qwen3-ASR-Flash-Realtime

  • Paraformer Speech Recognition

  • Multimodal Interaction Lightweight Speech Recognition

  • Qwen3-TTS-Flash-Realtime Qianyue

  • Qwen3-TTS-Flash-Realtime

  • Multimodal Interaction Lightweight Speech Synthesis

Korean

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

  • Paraformer Speech Recognition

  • Multimodal Interaction Lightweight Speech Recognition

  • Qwen3-TTS-Flash-Realtime Qianyue

  • Qwen3-TTS-Flash-Realtime

  • Multimodal Interaction Lightweight Speech Synthesis

French

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

  • Paraformer Speech Recognition

  • Multimodal Interaction Lightweight Speech Recognition

  • Qwen3-TTS-Flash-Realtime Qianyue

  • Qwen3-TTS-Flash-Realtime

  • Sambert Speech Synthesis Model

German

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

  • Paraformer Speech Recognition

  • Multimodal Interaction Lightweight Speech Recognition

  • Qwen3-TTS-Flash-Realtime Qianyue

  • Qwen3-TTS-Flash-Realtime

  • Sambert Speech Synthesis Model

Italian

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-TTS-Flash-Realtime Qianyue

  • Qwen3-TTS-Flash-Realtime

  • Sambert Speech Synthesis Model

Spanish

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-TTS-Flash-Realtime Qianyue

  • Qwen3-TTS-Flash-Realtime

  • Sambert Speech Synthesis Model

Portuguese

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-TTS-Flash-Realtime Qianyue

  • Qwen3-TTS-Flash-Realtime

Russian

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

  • Paraformer Speech Recognition

  • Multimodal Interaction Lightweight Speech Recognition

  • Qwen3-TTS-Flash-Realtime Qianyue

  • Qwen3-TTS-Flash-Realtime

Thai

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

  • Sambert Speech Synthesis Model Waan

  • Sambert Speech Synthesis Model

Indonesian

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

  • Sambert Speech Synthesis Model Indah

  • Sambert Speech Synthesis Model

Filipino

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Cantonese

  • Fun-ASR Real-time Speech Recognition

  • Qwen3-ASR-Flash-Realtime

  • Fun-ASR Real-time Speech Recognition

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-TTS-Flash-Realtime Qianyue

  • Qwen3-TTS-Flash-Realtime

  • CosyVoice-v3-Flash Large Model

  • Multimodal Interaction Lightweight Speech Synthesis

Arabic

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Hindi

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Turkish

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Ukrainian

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Czech

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Danish

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Finnish

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Icelandic

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Norwegian

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Polish

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Dutch

Currently requires integration with a third-party model

Currently requires integration with a third-party model

Swedish

  • Qwen3-ASR-Flash-Realtime

  • Qwen3-ASR-Flash-Realtime

Configuration

  1. In the console, click to create a "Multimodal Application".

  2. Select the desired language and category to create the application. The system will provide the most suitable models, prompts, and feature combinations.

    In this example, for Conversation language select English, and for the scenario template select AI Glasses.

  3. Adjust the prompt and other content based on your business scenario. Features unavailable for the current language are hidden.

    On the Speech Interaction tab, you can configure speech recognition (such as Fun-ASR Real-time Speech Recognition) and speech synthesis (such as the CosyVoice-v3-Flash Large Model), as well as options such as hotwords, instant correction, and conversation interruption (barge-in at any time/full-duplex, or click-to-interrupt/half-duplex). On the Understanding and Generation tab, you can configure options such as intent recognition, the text model (such as Qwen3.6-Plus), follow-ups, the knowledge base, web search, and long-term memory. The page also contains the Skills and Agent tabs for further configuration.

  4. Click "Run Now", browse the available timbre list in the timbre selection area of the run panel on the right, and select a suitable timbre.

  5. Test the conversation on the right, and proceed with subsequent steps such as publishing, development integration, and purchase.