Text to Speech | Vidu API

Audio Generating

This API is used to generate speech audio from input text, with controllable speech speed, volume, and emotion.

POST https://api.vidu.com/ent/v2/audio-tts

Field	value	Description
Content-Type	application/json	Data Exchange Format
Authorization	Token {your api key}	Replace {} with your API key

Field	Type	Required	Description
text	String	Required	The text to be synthesized into speech. 1. Length must be less than 10,000 characters. 2. Paragraph breaks are marked by newline characters. 3. Pause control: supports custom time intervals between text segments to achieve customized speech pauses. - Usage: insert <#x#> in the text, where x is the pause duration (unit: seconds), range [0.01, 99.99], up to two decimal places.Pause markers must be placed between two pronounceable text segments and cannot be used consecutively. - Example: Hello<#2#>I am vidu<#2#>Nice to meet you
voice_setting_voice_id	String	Required	Voice ID used for synthesis.See the Voice List for all available voices.
voice_setting_speed	Float	Optional	Speech speed, default is 1.0. 1.0 means normal speed; range [0.5, 2]. A value of 0.5 is the slowest, and 2 is the fastest.
voice_setting_volume	Int	Optional	Volume level. Range 0–10, default is 0 (normal volume). Higher values increase volume.
voice_setting_pitch	Int	Optional	Pitch of the synthesized audio. Range [-12, 12], default 0. 0 represents the original pitch.
voice_setting_emotion	String	Optional	Emotion of the synthesized voice. 1. Possible values: ["happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm"], corresponding to 7 emotions: happy, sad, angry, fearful, disgusted, surprised, and neutral. 2. The model will automatically match an appropriate emotion based on the text, so manual selection is usually unnecessary.
payload	String	Optional	Pass-through parameter. No processing, used for data transmission only.Max length: 1,048,576 characters.

Field	Type	Description
task_id	String	Task ID generated by Vidu
state	String	It will be returned to a specific processing state: - queueing task in queue - success generation successful - failed task failed
file_url	String	URL of the generated audio file
credits	Int	Number of credits consumed for this request
payload	String	Pass-through parameter value from the request
created_at	String	Task creation time

{
  "task_id": "your_task_id_here",
  "state": "success",
  "file_url": "your_file_url_here",
  "credits": ,
  "payload":"",
  "created_at": "2025-01-01T15:41:31.968916Z"
}

Field

value

Description

Content-Type

application/json

Data Exchange Format

Authorization

Token {your api key}

Replace {} with your API key

Field	Type	Required	Description
text	String	Required	The text to be synthesized into speech. 1. Length must be less than 10,000 characters. 2. Paragraph breaks are marked by newline characters. 3. Pause control: supports custom time intervals between text segments to achieve customized speech pauses. - Usage: insert <#x#> in the text, where x is the pause duration (unit: seconds), range [0.01, 99.99], up to two decimal places.Pause markers must be placed between two pronounceable text segments and cannot be used consecutively. - Example: Hello<#2#>I am vidu<#2#>Nice to meet you
voice_setting_voice_id	String	Required	Voice ID used for synthesis.See the Voice List for all available voices.
voice_setting_speed	Float	Optional	Speech speed, default is 1.0. 1.0 means normal speed; range [0.5, 2]. A value of 0.5 is the slowest, and 2 is the fastest.
voice_setting_volume	Int	Optional	Volume level. Range 0–10, default is 0 (normal volume). Higher values increase volume.
voice_setting_pitch	Int	Optional	Pitch of the synthesized audio. Range [-12, 12], default 0. 0 represents the original pitch.
voice_setting_emotion	String	Optional	Emotion of the synthesized voice. 1. Possible values: ["happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm"], corresponding to 7 emotions: happy, sad, angry, fearful, disgusted, surprised, and neutral. 2. The model will automatically match an appropriate emotion based on the text, so manual selection is usually unnecessary.
payload	String	Optional	Pass-through parameter. No processing, used for data transmission only.Max length: 1,048,576 characters.

Field	Type	Description
task_id	String	Task ID generated by Vidu
state	String	It will be returned to a specific processing state: - queueing task in queue - success generation successful - failed task failed
file_url	String	URL of the generated audio file
credits	Int	Number of credits consumed for this request
payload	String	Pass-through parameter value from the request
created_at	String	Task creation time

{
  "task_id": "your_task_id_here",
  "state": "success",
  "file_url": "your_file_url_here",
  "credits": ,
  "payload":"",
  "created_at": "2025-01-01T15:41:31.968916Z"
}

Search documentation

Search documentation