Available now

Kling TTS: text to speech

By Kuaishou

Kling TTS reads up to 500 characters of text in one of its preset voices, at a speed you set.

Model ID
Maker
Kuaishou

Input

Fields marked * are required. Review the price before generating.

The text to be converted to speech

Example. Edit it or write your own.

Additional settings

The voice ID to use for speech synthesis

Rate of speech

Price$0.02 / run

You sign up first. Your settings are kept.

About this model

Overview

Kling TTS turns a short text into speech. Choose a preset voice, from narrators and story readers to cartoon characters, and set the speaking rate from a little slower than normal to twice as fast.

What you can build

  • Short voice lines for video clips
  • Character voices for animations and cartoons
  • Story narration in short parts
  • Spoken captions for social posts

Prompting tips

  • Split longer scripts into parts that fit the character limit and keep the same voice for each part.
  • Try a few voices with one line before reading the full script.
  • Raise the speed only a little for ads; very fast reads are harder to follow.

What to check

Listen to the complete audio and check pronunciation, lyrics, timing and sound quality.

Inputs

  • Text (required): The text to be converted to speech.
  • Voice Id (optional): The voice ID to use for speech synthesis. Options: Voice 1, Student, Voice 3, Voice 4, Voice 5, Voice 6, Voice 7, Male 1, Voice 9, Girlfriend 4, Chat, female, Chat 2, Cartoon boy, British boy, Cartoon girl, Cartoon character, Voice 17, Voice 18, Old king, Mature woman, Calm, Calm storyteller, British man, Grandmother, Kind grandmother, Reader, male (English), Commercial, female (English), Sports student, Caring boyfriend, Girlfriend 1, Girlfriend 2, Host, British old man, Northeastern man, Chongqing young man, Sichuan young woman, Chaoshan uncle, Taiwanese man, Shopkeeper, Tianjin woman, Deep male voice, Gentle young man, Young woman, Sweet student, Narrator, Cute child.
  • Voice Speed (optional): Rate of speech. From 0.8 to 2.

Output and limits

  • Sung or spoken words can come out unclear or differ from your text.
  • Exact length, tempo and key are not guaranteed; listen to the whole result before you use it.
  • Prompts that name real artists or protected songs can be refused.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • up to, default options: $0.02 / run