Reach 125K+ monthly visitors
Advertise on TrendshiftText to speech
SOTA Hinglish (89M) code-switching TTS, fully in the browser on WebGPU
AI-powered podcast-to-video pipeline. Semantic B-roll, voice synthesis, burned subtitles, YouTube publishing.
Hear your coding agent. claude-tts speaks a curated, filtered stream of a Claude Code agent's work — the status pivots, the errors, the final answers — and stays quiet through the noise.
AI live commentator for sports streams. It watches the Agora RTC video feed and adds AI voice commentary.
THE EASIEST AI VTUBER TO SETUP KNOWN TO MAN.
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
Portable C++17 implementation of mispeech/Dasheng-AudioGen a 2B-parameter flow-matching text-to-audio model using GGML
A local-first, open-source voice assistant with a wake word, swappable models, and opt-in tools — built on Pipecat.
Local AI voice narrator for VtM: Night Road
An integrated X/Twitter experience enhancer by consolidating multiple browser extensions.
MCP server + CLI to generate image, video, music and speech through Chutes, saved straight into your project.
An O'RLY-parody bookshelf of AI-generated, narrated data-flow explainers
Vapi voice-search agent for the LocallySells tobacco-delivery marketplace (hackathon)
A companion app for Gothic 1 Remake that solves chest lock puzzles and guides you through the solution step by step
A small benchmark harness for testing voice-language disentanglement in multilingual text-to-speech systems.
local first first chrome extension that reads to you with a follow along