Generate controllable speech in 20 Indian languages and English by supplying the transcript and a natural-language description of the voice and recording. Indic Parler-TTS is developed by AI4Bharat. Adjust the available settings to shape the result for your task.
Model
ai4bharat/indic-parler-tts
Documentation
Use this reference to understand how every field in the playground changes the request sent to ai4bharat/indic-parler-tts.
Required
Type: Text
Provides the exact transcript the speech model will read aloud. Write the words, punctuation, and language you want spoken; punctuation can influence pauses and phrasing, while pronunciation still depends on the model’s training data.
Required
Type: Text
Describes how the generated voice and recording should sound rather than what it should say. Specify speaker characteristics, pitch, pace, emotion, clarity, distance, and background noise; concrete acoustic details provide more useful control than subjective labels alone.