Text → natural speech
Paste up to 30,000 characters of Hindi, Marathi (Devanagari) or English. It is chunked, synthesized and stitched into a single narration.
Same text, same voice, same GPU. The only difference is the pipeline. Press play, then flip between Before and After: the playhead stays in place, so you hear the same moment both ways.
Text → natural speech
Paste up to 30,000 characters of Hindi, Marathi (Devanagari) or English. It is chunked, synthesized and stitched into a single narration.
Zero-shot voice cloning
A 10–30 s reference recording is enough. The pipeline cleans it and picks the best 10 s for the model.
Runs on a laptop
Built and measured on an RTX 3050 6 GB laptop GPU, with one resident model and a single-GPU job queue.
Responsible by default
Consent is required for custom voices. Every output carries a watermark and AI-generated metadata tags.
Punctuation, abbreviations, markdown, numbers
Sentence & Danda (।) aware, ≤220 chars; mid-sentence cuts keep a comma
De-clip, de-rumble, light denoise, pick the best 10 s window
Resident model, cached voice conditioning, tuned settings
Babble, truncation and dead-air detection; one retry with a new seed
Trim, level-match, pauses by punctuation, filled with room tone
Two-pass loudness to −16 LUFS + AI-attribution tags in one encode
Exactly two files: WAV master + MP3