Speech-to-speech models

​

S2S vs pipeline

Two ways to build voice-enabled apps:

• Use S2S when interactive conversation, low latency, and audio-aware responses matter. Continue reading this page.
• Use Pipeline when you need custom voices or want to mix-and-match the best ASR, LLM, and TTS for each stage.

​

Real-time or file-based?

• Real-time (WebSocket) — Use for live voice interfaces: voice assistants, call centers, simultaneous interpretation. Audio streams in, speech streams out. Model names contain -realtime.
• File-based (HTTP) — Use when you can trade latency for better results: video dubbing, podcast translation, offline content processing. Unlocks function calling (Qwen3.5-Omni, Qwen3-Omni-Flash), web search (Qwen3.5-Omni), thinking mode (Qwen3-Omni-Flash), and video context (Livetranslate).

​

Function calling

Let the model take actions based on what it hears and sees — check a knowledge base, query a schedule, trigger a workflow. Use qwen3.5-omni-plus (HTTP), qwen3.5-omni-flash (HTTP), or qwen3-omni-flash (HTTP). Not available on realtime or Livetranslate models.

​

Web search

Let the model retrieve real-time information to answer questions about current events, stock prices, weather, and more. Use qwen3.5-omni-plus (HTTP) or qwen3.5-omni-plus-realtime (WebSocket). The model autonomously decides whether to search. Not available on Qwen3-Omni-Flash or Livetranslate models.

​

Thinking mode

Use qwen3-omni-flash (HTTP) when answer quality matters more than latency. The model reasons step-by-step before producing speech — useful for technical support, complex Q&A, or multi-step instructions. Not available on Qwen3.5-Omni models.

​

Translation

All three model families can translate speech:

• Qwen3-Livetranslate — 18 languages + 5 Chinese dialects, ~3-second latency, out of the box. File-based variant accepts video for context-aware accuracy. 7 languages output text only (no audio).
• Qwen3.5-Omni — 29 output languages + 7 Chinese dialects. Superior audio-video understanding and web search. Inject terminology and domain context via system prompt. Both realtime and file-based.
• Qwen3-Omni-Flash — 11 output languages + 8 Chinese dialects. Inject terminology and domain context via system prompt for specialized fields. Both realtime and file-based. Lower cost.

Supported languages

Language	Qwen3-Livetranslate	Qwen3.5-Omni	Qwen3-Omni-Flash
English	✓	✓	✓
Chinese (Mandarin)	✓	✓	✓
+ Cantonese	✓	✓	✓
+ Sichuanese	✓	✓	✓
+ Shanghainese	✓	✓	✓
+ Beijing	✓	✓	✓
+ Tianjin	✓	✓	✓
+ Nanjing	—	✓	✓
+ Shaanxi	—	✓	✓
+ Hokkien	—	✓	✓
French	✓	✓	✓
German	✓	✓	✓
Russian	✓	✓	✓
Italian	✓	✓	✓
Spanish	✓	✓	✓
Portuguese	✓	✓	✓
Japanese	✓	✓	✓
Korean	✓	✓	✓
Thai	Text only	✓	✓
Indonesian	Text only	✓	—
Vietnamese	Text only	✓	—
Arabic	Text only	✓	—
Hindi	Text only	✓	—
Turkish	Text only	✓	—
Finnish	—	✓	—
Polish	—	✓	—
Dutch	—	✓	—
Czech	—	✓	—
Urdu	—	✓	—
Tagalog	—	✓	—
Swedish	—	✓	—
Danish	—	✓	—
Hebrew	—	✓	—
Icelandic	—	✓	—
Malay	—	✓	—
Norwegian	—	✓	—
Persian	—	✓	—
Greek	Text only	—	—

✓ = audio + text output. "Text only" = no audio output for that language.Qwen3.5-Omni supports 113 input languages/dialects total. See full list for details.Legacy qwen-omni-turbo supports Chinese and English only.

​

Recommended models

​

All models

​

Learn more