Qwen3 TTS Flash - ShuYou Docs

curl --request POST \
  --url https://api.shuyou.ai/v1/predictions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen3-tts-flash",
  "function": "audio",
  "input": {
    "prompt": "At the jet bridge, Leo took his first step onto the metal walkway. He could smell faint fumes from the runway. The plane loomed ahead like a quiet animal. As he approached the door, he paused, gave the flight attendant a small smile, and entered the long, low-lit cabin.Engines roared. Leo grasped the armrest as the plane gathered speed and lifted into the sky. The city below shrank into a dim grid of lights. At cruising altitude, the engines settled into a low hum. The atmosphere outside felt thin and silent.",
    "voice": "Cherry",
    "language": "Auto"
  },
  "webhook": "https://api.shuyou.ai/backend/api/callback"
}
'

{
  "data": {
    "task_id": "2c4d50261173430290971a2395a3b607",
    "task_status": "processing"
  }
}

POST

predictions

curl --request POST \
  --url https://api.shuyou.ai/v1/predictions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen3-tts-flash",
  "function": "audio",
  "input": {
    "prompt": "At the jet bridge, Leo took his first step onto the metal walkway. He could smell faint fumes from the runway. The plane loomed ahead like a quiet animal. As he approached the door, he paused, gave the flight attendant a small smile, and entered the long, low-lit cabin.Engines roared. Leo grasped the armrest as the plane gathered speed and lifted into the sky. The city below shrank into a dim grid of lights. At cruising altitude, the engines settled into a low hum. The atmosphere outside felt thin and silent.",
    "voice": "Cherry",
    "language": "Auto"
  },
  "webhook": "https://api.shuyou.ai/backend/api/callback"
}
'

{
  "data": {
    "task_id": "2c4d50261173430290971a2395a3b607",
    "task_status": "processing"
  }
}

Voice presets (`input.voice`)

Pass a voice preset name in input.voice. The table below lists Qwen TTS voices supported by qwen3-tts-flash (and related Qwen TTS model families).

`voice`	Name	Description	Languages
`Cherry`	芊悦	Sunny, upbeat, natural female	Mandarin, English, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean
`Serena`	苏瑶	Gentle female	Same as above
`Ethan`	晨煦	Warm, energetic male (Mandarin with slight northern accent)	Same as above
`Chelsie`	千雪	Anime-style virtual girlfriend (female)	Same as above
`Momo`	茉兔	Playful, teasing female	Same as above
`Vivian`	十三	Cute but feisty female	Same as above
`Moon`	月白	Cool, handsome male	Same as above
`Maia`	四月	Intellectual and gentle female	Same as above
`Kai`	凯	Soothing male	Same as above
`Nofish`	不吃鱼	Designer male (non-retroflex accent)	Same as above
`Bella`	萌宝	Cute young female	Same as above
`Jennifer`	詹妮弗	Cinematic American female	Same as above
`Ryan`	甜茶	Dramatic, expressive male	Same as above
`Katerina`	卡捷琳娜	Mature female	Same as above
`Aiden`	艾登	American male	Same as above
`Eldric Sage`	沧明子	Wise elder male	Same as above
`Mia`	乖小妹	Obedient, gentle female	Same as above
`Mochi`	沙小弥	Precocious young male	Same as above
`Bellona`	燕铮莺	Powerful, clear female (period drama style)	Same as above
`Vincent`	田叔	Husky, gritty male	Same as above
`Bunny`	萌小姬	Very cute young female	Same as above
`Neil`	阿闻	Professional news anchor male	Same as above
`Elias`	墨讲师	Educational female narrator	Same as above
`Arthur`	徐大爷	Folksy storyteller male	Same as above
`Nini`	邻家妹妹	Sweet younger-sister female	Same as above
`Seren`	小婉	Calm, sleep-aid female	Same as above
`Pip`	顽屁小孩	Mischievous boy	Same as above
`Stella`	少女阿月	Sweet magical-girl female	Same as above
`Bodega`	博德加	Warm Spanish uncle (male)	Same as above
`Sonrisa`	索尼莎	Cheerful Latina female	Same as above
`Alek`	阿列克	Russian male	Same as above
`Dolce`	多尔切	Laid-back Italian uncle (male)	Same as above
`Sohee`	素熙	Warm Korean female	Same as above
`Ono Anna`	小野杏	Feisty childhood-friend female	Same as above
`Lenn`	莱恩	Rational German youth (male)	Same as above
`Emilien`	埃米尔安	Romantic French male	Same as above
`Andre`	安德雷	Magnetic, steady male	Same as above
`Radio Gol`	拉迪奥·戈尔	Sports commentator male	Same as above
`Jada`	上海-阿珍	Shanghai dialect female	Shanghai dialect + same multilingual set
`Dylan`	北京-晓东	Beijing dialect male	Beijing dialect + same multilingual set
`Li`	南京-老李	Nanjing dialect male	Nanjing dialect + same multilingual set
`Marcus`	陕西-秦川	Shaanxi dialect male	Shaanxi dialect + same multilingual set
`Roy`	闽南-阿杰	Taiwanese Hokkien male	Hokkien + same multilingual set
`Peter`	天津-李彼得	Tianjin dialect male (comic duo style)	Tianjin dialect + same multilingual set
`Sunny`	四川-晴儿	Sichuan dialect female	Sichuan dialect + same multilingual set
`Eric`	四川-程川	Sichuan dialect male	Sichuan dialect + same multilingual set
`Rocky`	粤语-阿强	Cantonese male	Cantonese + same multilingual set
`Kiki`	粤语-阿清	Cantonese female	Cantonese + same multilingual set

Language (`input.language`)

Optional. Sets the synthesis language (Qwen API field: language_type). Default Auto.

Value	When to use
`Auto`	Mixed-language text or uncertain language. The model matches pronunciation per segment; accuracy is not guaranteed.
`Chinese`	Single-language Chinese text — typically better quality than `Auto`
`English`	Single-language English text
`German`	Single-language German text
`Italian`	Single-language Italian text
`Portuguese`	Single-language Portuguese text
`Spanish`	Single-language Spanish text
`Japanese`	Single-language Japanese text
`Korean`	Single-language Korean text
`French`	Single-language French text
`Russian`	Single-language Russian text

For monolingual content, specify the language explicitly instead of Auto for best results.

Authorizations

Authorization

string

header

required

Authorization: Bearer YOUR_API_KEY

Body

application/json

model

enum<string>

default:qwen3-tts-flash

required

Model ID. Use qwen3-tts-flash for this endpoint.

Available options:

qwen3-tts-flash

Example:

"qwen3-tts-flash"

function

enum<string>

required

Task type. Must be audio for text-to-speech.

Available options:

audio

Example:

"audio"

input

object

required

Show child attributes

webhook

string<uri>

Optional HTTPS callback URL when the task completes, fails, or is cancelled.

Response

Async task created

data

object

required

Show child attributes

MiniMax Speech 2.8 HD Veo 3.1 Lite Generate Preview

​Voice presets (input.voice)

​Language (input.language)

Authorizations

Body

Response

Voice presets (`input.voice`)

Language (`input.language`)