replicate / audio
qwen3-tts
A unified Text-to-Speech demo featuring three powerful modes: Voice, Clone and Design
qwen/qwen3-tts
来源检查时间: 2026-09-13 · 供应商端点记录，不代表独立效果评测。
价格与适用条件。
以下是来源观察记录，不能直接相互替代。Token、计算耗时、输出时长与按次价格不能仅比较数值；输入和可选功能可能另行计费。
| 来源标价 | 计费单位 | 条件 | 依据 |
|---|---|---|---|
| $0.02 USD | input character | or 50,000 characters for $1 | 公开结构化来源 |
来源提供的参数
| language | Language of the text (use 'auto' for automatic detection) · Options: auto, Chinese, English, Japanese, Korean, French, German, Italian, Spanish, Portuguese, Russian · Default: auto |
|---|---|
| reference_audio | Reference audio file for voice cloning (only for 'voice_clone' mode) |
| voice_description | Natural language description of desired voice (only for 'voice_design' mode). Example: 'A warm, friendly female voice with a slight British accent' |
未列出的参数、地区可用性、最低充值、税费和商用条款仍待核实，购买前请核对精确端点。