Announcing transcribe.cpp

Meet transcribe.cpp, a new open-source C/C++ speech-to-text inference library with portable, GPU-accelerated support for multiple STT models. Developed through Mozilla.ai's Builders in Residence program, it makes adding fast, local transcription to applications easier than ever.

ICML WhisperKit: On-device Real-time ASR with Billion-Scale Transformers

Real-time Automatic Speech Recognition (ASR) is a fundamental building block for many commercial applications of ML, including live captioning, dictation, meeting transcriptions, and medical scribes. Accuracy and latency are the most important factors when companies select a system to deploy. We present WhisperKit, an optimized on-device inference system for real-time ASR that significantly outperforms leading cloud-based systems. We benchmark against server-side systems that deploy a diverse set of models, including a frontier model (OpenAI gpt-4o-transcribe), a proprietary model (Deepgram nova-3), and an open-source model (Fireworks large-v3-turbo).Our results show that WhisperKit matches the lowest latency at 0.46s while achieving the highest accuracy 2.2\% WER. The optimizations behind the WhisperKit system are described in detail in this paper.

\robotoslablightdots.tts Technical Report

Text-to-speech (TTS) systems have largely solved intelligibility on standard read-speech benchmarks. What users expect from a modern system is broader: expressive and controllable output, real-time synthesis, and coverage of neutral reading, emotional dialogue, paralinguistic events, singing, and general audio. Current systems pursue this goal along three roughly distinct technical routes, and each route has its own unresolved problem.

DeepL AI Platform: Translation, Voice & API

Explore our AI suite and get more done: Translate speech, text, and media, or integrate the DeepL API.

Launching a free, open-source, on-device transcription app

TL;DR – Please try Moonshine Note Taker on your Mac! For years I’ve been telling people that AI wants to be local, that on-device models aren’t just a poor man’s alternative…

speakrail/speakrail

Speakrail - a low-latency fully-local voice assistant that runs on a single RTX 4090

OpenAI.fm

An interactive demo for developers to try the latest text-to-speech model in the OpenAI API

Coqui TTS & XTTS V2: AI Text to Speech in 8 Languages

Experience natural speech synthesis with Coqui TTS and XTTS V2 technology. Features voice cloning and support for 8 languages.

Handy

Handy is a cross platform, open-source, speech-to-text application for your computer

Introducing GPT-Live

A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.

Tiiny-AI/PowerInfer

High-speed Large Language Model Serving for Local Deployment

Build A Large Language Model (From Scratch), Published by Manning, ISBN 978-1633437166

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

ptr.pet/trill

creates video voice memos from audio clips; with bluesky integration.