Start creating

Qwen Audio 3 TTSAI text to speech

Alibaba's speech model, strong in Chinese and English. On Leap, it sits beside 174 other models in one studio.

  • Text to speech

Your words wait while you sign in.

  • No subscription
  • Every top model, one account
  • Pay per run, priced before it starts

Listen / Last ferry, pier four

0 / 11 s
Read the transcript

Good evening, passengers. The last ferry to the outer islands leaves from pier four in five minutes. Please keep your tickets ready, and please, stop feeding the gulls.

Listen / A platform announcement, in Mandarin

0 / 11 s
Read the transcript

各位旅客请注意,开往重庆北方向的列车即将进站,请站在黄色安全线以内,先下后上,注意脚下安全。

Listen / Dumplings, in Mandarin and English

0 / 13 s
Read the transcript

好,今天我们只做一件事: how to fold a dumpling that doesn't explode in the pot. 先拿一张皮,水不要太多,then pinch, pinch, pinch.

AI text to speech

Qwen Audio 3 TTS at a glance

Qwen Audio 3 TTS is a text-to-speech model from Alibaba. It makes speech from your text.

Made by
Alibaba
Makes
Speech
Starts from
Your text
Voices
45 to choose from
Text
Up to 2,000 characters
Price
$0.0675 per 1,000 characters
Updated
October 3, 2026
  1. 01Write the words, pick a voice
  2. 02See the exact price, then press go
  3. 03Keep it in your library, or take it further

Start with an idea

Three ways to try Qwen Audio 3 TTS

Why Leap

Why creators make it on Leap

  1. 01

    Every top model, side by side

    175 models from Black Forest Labs, Google, ByteDance, Kuaishou, Alibaba and more, side by side in one studio.

    See the models
  2. 02

    One click, or full control

    Character Studio, effects and recipes write the prompt for you. Or write your own for any model.

    See the tools
  3. 03

    Your work stays yours

    Everything you make stays in your library while your account is active, and you own what you make here.

    See what people make
  4. 04

    One balance for everything

    The studio, the API and your agents spend the same balance, and every run shows its price before it starts.

    How pricing works

Questions

Qwen Audio 3 TTS, answered

What is Qwen Audio 3 TTS?
Qwen Audio 3 TTS is a text-to-speech model from Alibaba. Alibaba's speech model, strong in Chinese and English. On Leap it runs in one studio beside every other top model, with one account.
Which voices can I use?
45 voices, among them Cherry, Serena, Ethan, Chelsie and Momo. You can hear each one in the studio before you run it.
How much text can it read in one run?
Up to 2,000 characters. You pay for the characters you send, with the price shown before you press go.
How much does a run cost?
It costs $0.0675 per 1,000 characters. You see the exact price before you press go, and a run that fails costs nothing.
Is Qwen Audio 3 TTS free to try?
No. There is no free credit: you add credit from $5, and your first top-up has no card fee. It costs $0.0675 per 1,000 characters. You pay per run, in dollars, with no subscription.
Can I use what I make commercially?
Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
Is there an API?
Yes. Leap's REST API runs it as alibaba/qwen-audio-3-tts, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
Do I need an Alibaba account?
No. Leap sends your request to Alibaba's model and gives you what it makes. One Leap account runs Qwen Audio 3 TTS and every other model, in the studio, through the API and from your agents.

Your idea, Qwen Audio 3 TTS.

Every run shows its price before it starts, and one that fails costs nothing.

Make it with Qwen Audio 3 TTS

For developers

Run Qwen Audio 3 TTS from code

Model ID
alibaba/qwen-audio-3-tts
Makes
Voice and sound
Pricing
Per run, quoted first: POST /v1/quotes

Inputs

What the model takes. Leave out anything with a default.

Texttext
Text, up to 2,000 characters, required
Voicevoice
Cherry, Serena, Ethan, Chelsie, Momo, Vivian, Moon, Maia, Kai, Nofish, Bella, Jennifer, Ryan, Katerina, Aiden, Mia, Mochi, Bellona, Vincent, Bunny, Neil, Elias, Arthur, Nini, Seren, Pip, Stella, Bodega, Sonrisa, Alek, Dolce, Sohee, Lenn, Emilien, Andre, Jada, Dylan, Li, Marcus, Roy, Peter, Sunny, Eric, Rocky, Kiki. Default: Cherry
Languagesettings.language
Auto, Chinese, English, Spanish, Russian, Italian, French, Korean, Japanese, German, Portuguese. Default: AutoLanguage of the input text.

The request

The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.

curl https://api.tryleap.ai/v1/generations \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "alibaba/qwen-audio-3-tts",    "input": {      "text": "Good evening, passengers. The last ferry to the outer islands leaves from pier four in five minutes. Please keep your tickets ready, and please, stop feeding the gulls."    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"