Models / IndexTTS 2.0
Bilibili · Voice

IndexTTS 2.0

Coming soon

Say how long the line has to run and it lands on it. The voice and the acting are set separately. Made by Bilibili. From $0.0022 a second of audio.

index-tts-2
TypeVoice
InputsText, Audio
From$0.0022 / s
UpdatedOct 12, 2026

Pricing

SettingMiniAPIfalDifference
any$0.0022 / s$0.002+10%

Parameters

NameRequiredValuesDefaultDescription
promptYestextWhat to make, in plain words.
audio_urlYeshttps URLThe sound to use.
emotional_audio_urlNohttps URLThe emotional reference audio file to extract the style from.
strengthNo0 to 11How much to change the input. Higher changes more.
should_use_prompt_for_emotionNotrue, falsefalseWhether to use the `prompt` to calculate emotional strengths, if enabled it will overwrite the `emotional_strengths` values. If `emotion_prompt` is provided, it will be used to instead of `prompt` to extract the emotional style.
emotion_promptNotextThe emotional prompt to influence the emotional style. Must be used together with should_use_prompt_for_emotion.
emotional_strengthsNoThe strengths of individual emotions for fine-grained control.
emotional_strengths.afraidNo0 to 1Strength of fear emotion
emotional_strengths.angryNo0 to 1Strength of anger emotion
emotional_strengths.calmNo0 to 1Strength of calm emotion
emotional_strengths.disgustedNo0 to 1Strength of disgust emotion
emotional_strengths.happyNo0 to 1Strength of happiness emotion
emotional_strengths.melancholicNo0 to 1Strength of melancholic emotion
emotional_strengths.sadNo0 to 1Strength of sadness emotion
emotional_strengths.surprisedNo0 to 1Strength of surprise emotion

FAQ

How much does IndexTTS 2.0 cost?

From $0.0022 per second of audio at any. Pricing lists every setting.

What inputs does IndexTTS 2.0 take?

Text, Audio.

Am I charged if a IndexTTS 2.0 job fails?

No. You are not charged for it.

Related models

All 74 models