All models

AlibabaVoice

Qwen Audio 3.0 TTS

Alibaba's speech model with 45 character voices.

voice/qwen-audio-3-tts
Try it in StudioUse with your agent or API

Momo, fox spirit

Hehe, found you! You can't hide from a fox spirit, you know. Now, what did you bring me?

Price
4.2 credits / minute
Typical time
about 6 s
Makes
Text to speech

Best for

Qwen Audio 3.0 TTS is Alibaba's speech model. It has 45 voices with a wide range of character, from cute and playful to calm and mature, and reads 11 languages.

  • Anime and cartoon style character voices.
  • Chinese, Japanese and Korean voice lines.
  • Short barks for pets, mascots and small creatures.

Put it together

Where Qwen Audio 3.0 TTS fits in a game, with the models it works well with. Your agent runs every step.

Price

ModeModelPrice
Text to speechQwen Audio 3.0 TTS4.2 credits / minute

Paid from your Summer credits.

Use it from code or your agent

Sign in once with summer login. Your agent or your code then runs it with your paid credits.

npx -y summer-engine@latest login
npx -y summer-engine@latest api run voice/qwen-audio-3-tts \
  --input '{"text":"The gate opens at dawn. Bring the lantern.","voiceId":"Cherry"}' \
  --download .

voice/qwen-audio-3-tts: $0.05 per 1,000 characters. Paid from your Summer credits.

Inputs

What input takes for voice/qwen-audio-3-tts. Send only what you need; Summer fills in tested defaults.

  • textstringRequired · up to 2000 characters

    The words to speak, at most 2000 characters.

  • voiceIdstringup to 100 characters

    Speech: a voice of the game cast.

  • voiceSettingsobject

    Speech: voice tuning.

    Show 5 child parameters
    • voiceSettings.stabilitynumber0 to 1
    • voiceSettings.similarityBoostnumber0 to 1
    • voiceSettings.stylenumber0 to 1
    • voiceSettings.speednumber0.7 to 1.2
    • voiceSettings.useSpeakerBoostboolean

Model docs · Summer API docs · Set up the Summer MCP server · Try it in the browser

Questions

What is Qwen Audio 3.0 TTS good for in game development?
Qwen Audio 3.0 TTS is Alibaba's speech model. It has 45 voices with a wide range of character, from cute and playful to calm and mature, and reads 11 languages. Typical game uses: anime and cartoon style character voices; chinese, Japanese and Korean voice lines; short barks for pets, mascots and small creatures.
How much does Qwen Audio 3.0 TTS cost in Summer?
Qwen Audio 3.0 TTS costs 4.2 credits / minute in Summer Studio. It is charged from your Summer credits.
What kind of audio can Qwen Audio 3.0 TTS make?
In Summer, Qwen Audio 3.0 TTS is used for text to speech.
Can I use Qwen Audio 3.0 TTS from Claude Code, Cursor or Codex?
Yes. Connect the Summer MCP server to Claude Code, Cursor, Codex or another MCP client, then ask your agent to generate with summer_generate_audio with capability: "text_to_speech", modelId: "qwen-audio-3-tts". Setup instructions are at summerengine.com/mcp.
Where do Qwen Audio 3.0 TTS results go?
Every generation is saved to your Summer asset library. From there you can download it or bring it into a Summer Engine project.