Fine-tuned Parler-TTS (600M) for Hinglish language, Indian accent, and emotion-conditioned speech synthesis. Published at arXiv:2506.16310.
-
Updated
Mar 26, 2026 - Jupyter Notebook
Fine-tuned Parler-TTS (600M) for Hinglish language, Indian accent, and emotion-conditioned speech synthesis. Published at arXiv:2506.16310.
Text-to-speech MCP server — 48 voices, 9 languages, 5 presets, emotion spans, SSML-lite, multi-speaker dialogue, SFX tags, and built-in guardrails.
Add a description, image, and links to the emotion-synthesis topic page so that developers can more easily learn about it.
To associate your repository with the emotion-synthesis topic, visit your repo's landing page and select "manage topics."