Actions24
- Audio Actions
- Image Actions
- Video Actions
- Animate Mix | 视频换人
- Animate Move | 图生动作
- Emoji Video | Emoji 视频生成
- Image to Video (First & Last Frames) | 图生视频(首尾帧)
- Image to Video (First Frame) | 图生视频(首帧)
- Video Continuation | 视频续写
- Reference to Video | 参考生视频(wan2.6)
- Text to Video | 文生视频
- Video Editing & Effects | 视频编辑与特效
- Video Retalk (Lip Sync) | VideoRetalk 口型复刻
- Task Actions
- Vision Actions
- File Actions
Audio → Text to Speech | 文本转语音
AI-generatedSummary
Convert given text into synthesized speech audio using a selected TTS model, voice, and language.
Inputs
- Model | 模型 (required) — Select the text-to-speech model to use; options include the multi-language Qwen3-TTS Flash and the basic Qwen-TTS which supports only Chinese and English.
- Text | 文本 (required) — Provide the text content you want to synthesize into speech. Recommended to keep text within 600 characters.
- Voice Name or ID | 音色名称或 ID (required) — Select a voice from the list of available voices for the chosen model or specify a voice ID via expression.
- Language Name or ID | 语言名称或 ID (required) — Select the target language for speech synthesis, matching the model capabilities, or specify a language ID via expression.
Output shape
a single synthesized audio file or audio data stream representing the spoken version of the input text.
The output corresponds to the synthesized speech generated using the specified TTS model, voice, and language. Text length constraints and model capabilities may affect synthesis. Voice and language options dynamically load depending on the selected model.