@pratyushchauhan

supertonic-tts synthesizes speech on-device via onnx across 31 languages, runs at 167x realtime on consumer hardware, and supports voice cloning through an online service. no api key required for base synthesis.

data-chart-builder generates publication-ready charts from csv, json, fred api, or inline data with support for line, bar, scatter, and area-fill plots. config-driven workflow with indexing, annotations, and multi-series overlays for economic and time-series analysis.

Generate animated conversation videos with multi-voice TTS audio and timed text overlays. Use when the user needs to (1) turn a transcript or dialogue into a...

A video skill for agents. Build animated videos programmatically using Remotion. Use when the user wants to (1) make any kind of animated video — intros, exp...

Create publication-ready economic comparison charts from Federal Reserve Economic Data (FRED). Use when the user needs to visualize, compare, or analyze econ...