Turn a PDF into a narrated MP3 via Replicate Inworld TTS — chunk, cache, concat.
Updated 2026-05-14 07:07:15 +00:00
Fork of NousResearch/hermes-agent for custom TTS and voice cloning development
Updated 2026-05-14 06:00:10 +00:00
Objective per-clip audio metrics for voice samples (RMS, peak, clipping, crest, score) — companion to preset-audition
Updated 2026-05-13 07:03:52 +00:00
Measure round-trip CoreAudio device latency via chirp + cross-correlation (macOS, BlackHole-aware).
Updated 2026-05-13 00:55:37 +00:00
Render voice-mode presets (Dry/Man/Woman/Child/Old) against a sample and emit an HTML A/B audition page. ffmpeg-only.
Updated 2026-05-11 07:04:10 +00:00
Diagnose macOS audio routing for real-time voice DSP (BlackHole + Zoom/Teams).
Updated 2026-05-10 07:04:46 +00:00
Updated 2026-05-10 00:00:55 +00:00
Daily zero-config scanner for ML/AI/voice-DSP consulting & contract leads. Pure stdlib Python CLI.
Updated 2026-05-09 14:59:05 +00:00
Preview HUD content as the Even Realities G2 lens (576x288, 4-bit greyscale, green tint).
Updated 2026-05-08 07:03:04 +00:00
DGX Spark Ollama Leaderboard - benchmark suite for local LLM inference on NVIDIA DGX Spark
Updated 2026-05-08 06:17:34 +00:00
AdBlock Plus filter syntax to Apple Safari Content Blocker JSON converter
Updated 2026-05-07 07:03:59 +00:00
One-command narrated Manim explainers via Replicate Inworld TTS.
Updated 2026-05-06 07:04:05 +00:00
Multi-signal probe to estimate whether a SaaS has gone quiet.
Updated 2026-05-05 07:03:23 +00:00
Rank consulting/product opportunities from youtube-transcripts notes (CLI).
Updated 2026-05-04 07:04:09 +00:00
Multi-channel YouTube transcript archive — channels//transcripts/NN-
Updated 2026-05-04 05:34:15 +00:00
Offline auditioner for voice-enhancer pitch-shift presets (man/woman/child/old).
Updated 2026-05-03 07:03:56 +00:00
Updated 2026-04-27 00:30:43 +00:00
Updated 2026-04-05 22:34:26 +00:00