← All models

Qwen Voice-Design

Published Publisher Alibabaqwen-voice-design

Overview

Qwen Voice-Design is a Qwen speech-model service for creating a custom voice from a short text description. Used with qwen3-tts-vd-realtime, it can generate speech in 10 languages; the resulting speech can adapt its tone to the text. Potential uses include character voices, creative content and voice-assistant prototyping. (docs.modelstudio.console.alibabacloud.com)

Release and availability

  • Release date: December 12, 2025, as listed in the official model release log. (docs.modelstudio.console.alibabacloud.com)
  • Availability: Alibaba Cloud announced retirement of this legacy Model Studio model effective October 10, 2026, subject to the actual change time. The notice says calls will no longer return results after retirement and recommends cosyvoice-v3.5-flash as a replacement. Verify migration requirements before use. (alibabacloud.com)

Limitations

Voice design is distinct from cloning an existing voice: it starts from a text description rather than an audio sample. Multilingual speech output requires a compatible speech-synthesis model. The archived model documentation listed function calling, structured output, web search, context caching, batch inference and fine-tuning as unsupported; it did not specify context or input/output length limits. (help.aliyun.com)

Pricing

The following are historical official list prices, not a guarantee of current availability. The current pricing pages no longer list this model. Prices were checked on November 17, 2026.

  • Alibaba Cloud China site, Beijing: CNY 0.2 per newly created voice. The indexed official pricing page listed 10 free voices per account, subject to its 90-day free-quota conditions. China pricing page (help.aliyun.com)
  • Alibaba Cloud international site, Singapore, international deployment: USD 0.2 per newly created voice. The indexed official pricing page listed 10 free voices per account, subject to its 90-day free-quota conditions. The retirement notice described the price as USD 0.2 per call and showed no separate input charge. International pricing page; retirement notice. (alibabacloud.com)

These are per-voice or per-call charges, not input/output token rates. Subsequent synthesis using a designed voice is billed according to the selected synthesis model; its rate is separate. The CNY and USD listings apply to different billing sites and are not currency conversions. (help.aliyun.com)

Official sources