Remy Reference/Models/Text to speech/Qwen Audio 3.0 TTS Plus

Qwen Audio 3.0 TTS Plus

Qwen Audio 3.0 TTS Plus, a text-to-speech model from Alibaba Cloud.

speechModelOverride: { model: "qwen-audio-3.0-tts-plus" }

QQwen·served viaAlibaba Cloud·Released July 2026

Pricing

List price: $27.59 / 1M characters
Per 1M characters: $27.59
Per 1M characters: $0

Specifications

Context window: 10,000 tokens
Released: July 2026
Capabilities: Multilingual

Parameters

Model options, passed in speechModelOverride.config.

Parameter	Type	Default	Range / options
`voice` System voice to use. You can also paste a cloned or base voice id.	Select	longanlingxin	longanlingxinlonganlufeng
`instruction` Optional natural-language direction for delivery (emotion, pace, character). Leave blank for a neutral read.	Prompt	—	—
`rate` Speech rate. Default is 1.0.	Number	1	0.5–2, step 0.05
`pitch` Pitch. Default is 1.0.	Number	1	0.5–2, step 0.05
`format`	Select	mp3	mp3wav

Voices · 2

Longan Lingxin

warm, empathetic

Longan Lufeng

bright, cheerful

Use this model

await mindstudio.textToSpeech({
  text: "...",
  speechModelOverride: {
    model: "qwen-audio-3.0-tts-plus",
    config: {
      voice: "longanlingxin",
      rate: 1,
    },
  },
});