Alibaba Cloud Model StudioText-to-speech

qwen-audio-3.0-tts-flash

JSON

Qwen-Audio 3.0 TTS Flash TTS GA streaming, http, websocket

Previous-generation Qwen-Audio low-latency speech synthesis model.

01 Price

$15.00per 1M chars

Cheaper than 64% of 95 priced text-to-speech models.

Text-to-speech $ per 1M characters, log scale 95 priced, 193 without a USD price

Text-to-speech: 95 models with a published USD price per 1M characters, from $1 to $100 and beyond, shown on a log scale.

other models this modelAll models by price

Singapore (International deployment scope); listed as $0.15 per 10,000 characters; each Chinese character counts as 2.

Pricing source, checked 2026-11-16

02 Languages 18

03 Features 5 of 8 listed

"Not listed" means the provider's data doesn't mention it, not that the model lacks it.

04 Voices 12 compatible, browse all

  • Long An Feng Yue

    Natural and friendly

    female, 30 / Chinese +1
    Social companionship (premium Chinese voice)

    longanfengyue
  • Long An Huan

    female, 25 / Chinese +1

    longanhuan_v3.6
  • Long An Ling Xi

    Cute and sweet

    female, 25 / Chinese +1

    longanlingxi
  • Long An Xiao Xin

    Friendly and lively

    female, 22 / Chinese +1

    longanxiaoxin
  • Long An Yuan Fei

    Proud and regal

    female, 30 / Chinese +1

    longanyuanfei
  • Long Chuan Shu

    Sichuan-accented middle-aged male

    male, 40 / Chinese +1

    longchuanshu_v3.6

05 Get this record

curl https://voicedex.dev/v1/providers/alibaba/models/qwen-audio-3.0-tts-flash

Free, no key needed. Use model id qwen-audio-3.0-tts-flash with Alibaba Cloud Model Studio's own API. API reference.

Esc

↑↓ move↵ open