benchr

Launch record & analysis·July 2026

Qwen-Audio 3.0 TTS Plus: built-in voices are the product boundary

Plus is the built-in-voice branch of Qwen's new TTS line. Alibaba has not published token limits or a per-token price.

By the benchr team · · Changelog · Provider-published facts rechecked against the official sources on July 28, 2026

Five textured audio ribbons fan out from one shared source point.
Benchr model field plate Qwen Audio TTS Plus Preset voices · one palette
Editorial imageA BenchR editorial illustration of preset voice choice: distinct voice textures, one controlled audio palette.
Released14 Jul2026
Voice modeBuilt-inPreset voices
Token limit—Not published
Public price—Not published

Alibaba Cloud released Qwen-Audio 3.0 TTS Plus on July 14. Plus is the branch to inspect when you want built-in voices and do not need cloning.

Choose the voice workflow first

Alibaba positions Plus around standard synthesis with built-in voices, while Flash adds a cloning path. Decide whether a curated preset voice fits the product before comparing any broader quality claim. That choice may settle the endpoint immediately.

A demo sentence is too easy

Alibaba describes the model as instruction controlled. Test pronunciation, pacing, tone directions, names, numbers, markup removal, and language switching with scripts from your product. The edge cases shape perceived quality far more than a clean sample line.

The budget still has a blank

The checked release and TTS documentation identify the model and its role but list no public per-token price or token limits. Get the current commercial terms from Alibaba. Do not paste a rate from another speech service into the forecast.

Provider-published facts; documented gaps remain gaps
FieldVerified record
API model IDqwen-audio-3.0-tts-plus
AvailabilityAlibaba Cloud Model Studio
Voice approachBuilt-in voices
Public price / token limitNot published in checked docs

Frequently asked

What is Qwen-Audio 3.0 TTS Plus for?

Alibaba positions it for instruction-controlled standard speech synthesis with built-in voices.

Where is it available?

Alibaba lists it through Model Studio.

Does the checked documentation publish a token price?

No public per-token price or token limit was recorded from the checked official documentation.

Changelog

  • July 28, 2026 — Published after reviewing the official provider sources and recording unreported fields as gaps.

References

  1. Official release announcement or release notes: https://www.alibabacloud.com/help/en/model-studio/newly-released-models
  2. Official model documentation: https://www.alibabacloud.com/help/en/model-studio/tts-model/
Related