Tổng hợp giọng nói
POST
/ent/v2/audio-tts
- Tài liệu: https://platform.vidu.cn/docs/speech-synthesis
Authorizations
bearer
Type
HTTP (bearer)
Request Body
application/json
Text to synthesize
- Max length under 10000 characters
- Use line breaks for paragraphs
- Pause control: use <#x#> where x is pause duration in seconds, range [0.01, 99.99], max 2 decimal places. Place between speakable segments; do not chain multiple pause markers
- Example: Hello<#2#>I am vidu<#2#>Nice to meet you
Voice ID for synthesis
See voice list: https://shengshu.feishu.cn/sheets/EgFvs6DShhiEBStmjzccr5gonOg
Speech rate, default 1.0
1.0 is normal; range [0.5, 2]. 0.5 slowest, 2 fastest
Volume
Range 0–10, default 0 (normal). Higher = louder
Pitch
Range [-12, 12], default 0 (original voice)
Emotion for synthesized speech
- Allowed: "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm"
- Model usually auto-matches emotion from text
Pronunciation overrides for polyphones
- Rules for special readings; in Chinese, tones as digits 1–5
- Example:
["燕少飞/(yan4)(shao3)(fei1)", "达菲/(da2)(fei1)", "omg/oh my god"]
Passthrough parameter
Not processed; data transfer only
Note: Max 1048576 characters
Responses
Thành công
application/json