A demo of Indic Parler-TTS
Generate speech from text
High-fidelity Text-To-Speech
Convertir texto a audio
Sound effect from description
MP-SENet is a speech enhancement model.
StyleTTS2 trained on ukrainian dataset
Transcribe audio to text with timestamps
Generate speech from text with customizable options
Convert audio to text and summarize highlights
Generate natural-sounding speech from text using OpenAI's API
Spanish finetune for the original F5 model.
Generate speech using a speaker's voice
Indic Parler-TTS is a speech synthesis tool designed to generate audio from text and descriptions. It is part of the ParlAI project and focuses on supporting Indian languages to provide high-quality text-to-speech conversion. This tool is ideal for applications requiring natural-sounding audio outputs in multiple Indian languages.
What is Indic Parler-TTS used for?
Indic Parler-TTS is used to generate natural-sounding audio from text, particularly in Indian languages. It is suitable for content creation, educational purposes, and applications requiring multilingual speech synthesis.
Which languages are supported by Indic Parler-TTS?
Indic Parler-TTS supports multiple Indian languages. For the exact list, visit the official ParlAI documentation or the demo page.
How can I customize the voice and settings in Indic Parler-TTS?
Customization options, such as voice selection and speech rate adjustment, are available in the demo interface. Explore the settings menu to tailor the output to your preferences.