Back to Nodes
Kling Text To Speech

Kling Text To Speech

Official

Kling text-to-speech with voice selection and speed control.

Nodespell AI
AI / Audio / Kuaishou

Kling text-to-speech with voice selection and speed control.

Kling Text To Speech is a direct speech generator for short voice assets where the main choices are text, voice ID, and voice speed. It is useful when you are already working around Kling media and want a small TTS surface.

Use a more expressive speech node when style, emotion, language tuning, or script continuity controls are important.

Model Examples (3)

Example Index01 / 03
Example 01

Urgent voicemail

In-world dramatic message for a thriller or mystery scene.

Source Inputs01
Text

If you get this before sunrise, don't come through the front entrance. The keypad is dead, the cameras are looping, and somebody is already inside.

Parameters03
Text
If you get this before sunrise, don't come through the front entrance. The keypad is dead, the cameras are looping, and somebody is already inside.
Voice Id
oversea_male1
Voice Speed
0.98
ttscharacter
Response
Inputs (1)

Text

String

The text to be converted to speech

Multi InputMin: 0Max: 100
Parameters (3)

Text

String

The text to be converted to speech

Default:

Voice Id

String

The voice ID to use for speech synthesis

Default: genshin_vindi2

Voice Speed

Number

Rate of speech

Default: 1
Outputs (1)

Output

Inferred

Output

Nodespell Team

Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Audio / Kuaishou

Input

Text

Output

Audio

Keywords

Image GenerationLength ControlStructured Output
Use in Workflow