A developer created a spelling game using AI voice cloning and text-to-speech technology. They used VoxCPM2 and Chatterbox models via audio.cpp to generate word recordings in English, French, and Norwegian, but faced challenges with audio quality—words had incomplete beginnings or endings. They improved results by providing reference recordings and embedding isolated words within sentences to give the model context, then needed to precisely cut the audio at the right point to extract clean word recordings.
Jinfer is an AI inference engine for the JVM that enables running large language models, text-to-speech, audio transcription, and vision capabilities directly on Java using a modular, composable architecture. Distributed as lightweight dependencies, it allows developers to build AI applications with jbang scripts without external services.
Chronicle is a local-first, open-source authoring software designed for writers to manage the complete book creation process, from drafting to publication. It offers specialized tools for plotting timelines, building character and location databases, annotating manuscripts, designing covers, and exporting publication-ready formats including PDFs, ePubs, and Shunn manuscripts—all without cloud dependencies or paid subscriptions.
Nari Labs' Qwen3-TTS and Qwen3-ASR models rank at the top of Coval's voice AI benchmarks, achieving leading latency and accuracy metrics while offering competitive pricing. The Qwen3-ASR Fast model achieves 44ms latency and 3.6% word error rate for speech-to-text, while Qwen3-TTS Fast delivers 63ms latency and 3.8% WER for text-to-speech, both priced significantly lower than competitors like ElevenLabs and AssemblyAI.
Fish Audio is a free text-to-speech tool offering 300+ neural voices that converts up to 5,000 characters to MP3 without requiring sign-up, featuring instant preview and download capabilities for video editing.
Chickadee is a free, open-source browser extension that converts web pages to speech using a local AI model that runs entirely in your browser without uploading any data to servers. The extension uses Kokoro, an 82-million parameter speech model that downloads once (~310 MB) and works completely offline, with no accounts, API keys, or subscriptions required.