A demo of Indic Parler-TTS
Convert speech to text from audio files
Turn Any Article to Podcast
StyleTTS2 trained on ukrainian dataset
Whisper model to transcript japanese audio to katakana.
Realtime implementation of Whisper large turbo
Transcribe audio with emotions and events
CPU powered, low RTF, emotional, multilingual TTS
Generate realistic-sounding AI voice from text
Generate speech from text with reference audio
Simple Space for the Kokoro Model
Sound effect from description
Indic Parler-TTS is a speech synthesis tool designed to generate high-quality audio from text in multiple Indian languages. It leverages advanced AI technology to produce natural-sounding speech, making it ideal for applications such as education, content creation, and accessibility. This demo version provides a glimpse into the capabilities of text-to-speech conversion for Indian languages.
• Multi-language support: Generates speech in several Indian languages.
• High-quality audio: Produces natural and clear voice output.
• Customizable voices: Offers options to select different voices and tones.
• User-friendly interface: Easy to navigate and use for text-to-speech conversion.
• Real-time generation: Quickly converts text to audio for instant playback.
What languages are supported by Indic Parler-TTS?
Indic Parler-TTS supports a variety of Indian languages, including Hindi, Bengali, Telugu, Tamil, and more. The exact list may vary based on the version.
Can I use Indic Parler-TTS for commercial purposes?
The demo version is primarily for evaluation. For commercial use, please contact the developers for licensing options.
How do I download the generated audio?
After generating the audio, you should see an option to download the file in formats like MP3 or WAV, depending on the platform's capabilities.