https://www.fermionresearch.com/changelog/ Every release across Detta, the Phonon runtime, Core ML and our models, newest first. en Tue, 06 Oct 2026 00:00:00 GMT https://www.fermionresearch.com/changelog/#fermion-research-0-2-10 https://www.fermionresearch.com/changelog/#fermion-research-0-2-10 Tue, 06 Oct 2026 00:00:00 GMT Phonon runtime Phonon-2 starts much faster and decodes faster on Intel and AMD processors, on Linux and on Intel Macs, and uses less memory while it runs. Transcripts are unchanged, byte for byte. segments gives the start and end of every sentence or pause-sized stretch of speech, in --json and in the server's verbose_json, in the shape OpenAI clients already read. pip install fermion-research is now the whole setup on Linux, Windows and Intel Macs. On Apple silicon, pip install "fermion-research[mlx]" adds the MLX runtime. The CUDA image phonon-cuda:1.0.7 returns segments and word timestamps, and the CPU image phonon-cpu:2.0.8 runs this release on amd64 and arm64. https://www.fermionresearch.com/changelog/#detta-1-0-26 https://www.fermionresearch.com/changelog/#detta-1-0-26 Tue, 06 Oct 2026 00:00:00 GMT Detta Speech is recognised on your Mac's Neural Engine. Text appears faster after you speak, with a median of 0.26 seconds from key-up to text, down from 0.33, at the same accuracy. Detta holds about a sixth of the memory it did while it waits for you to talk. Your dictionary now steers recognition while it decodes, so names and terms you add are recognised more reliably. Long recordings are polished from the first word to the last and keep every sentence, and each word keeps its start and end time as the recording plays. The first time it runs, Detta lets you know while it sets up the Neural Engine for your Mac. Dictation works within about a minute. https://www.fermionresearch.com/changelog/#phonon-coreml-1-1-1 https://www.fermionresearch.com/changelog/#phonon-coreml-1-1-1 Tue, 06 Oct 2026 00:00:00 GMT Core ML The command-line tool reads any sample rate and the common audio formats, m4a included. --words prints every word on its own line with its start and end time. A clearer notice on the first run, and clearer error messages. https://www.fermionresearch.com/changelog/#fermion-research-0-2-9 https://www.fermionresearch.com/changelog/#fermion-research-0-2-9 Sun, 04 Oct 2026 00:00:00 GMT Phonon runtime Hotwords on every Phonon-2 engine. Give it up to 25 names and terms and it favours them whenever the audio is close. Without hotwords, every transcript is unchanged. --hotwords on the command line, hotwords= in Python, and a hotwords field on the server, which also reads the OpenAI prompt field as a vocabulary list. Hotwords work on Apple silicon, on Linux, Windows and macOS CPUs, and in the CUDA image phonon-cuda:1.0.6. Intel Macs run Phonon-2 on the CPU engine (0.2.8, first published in this release). https://www.fermionresearch.com/changelog/#phonon-2-coreml https://www.fermionresearch.com/changelog/#phonon-2-coreml Sun, 04 Oct 2026 00:00:00 GMT Core ML Phonon-2 for the Neural Engine, at the accuracy of the reference engine, 5.21 % average word error on the Open ASR Leaderboard's seven English test sets. On an M5 MacBook Air an hour of speech becomes text in 6 seconds, and the GPU stays free. Windows from 5 to 35 seconds share one set of weights, and every word carries its start and end time. A Swift package and command-line tool for macOS 15 and iOS 18 or later, and a Python runner. https://www.fermionresearch.com/changelog/#detta-1-0-24 https://www.fermionresearch.com/changelog/#detta-1-0-24 Sat, 03 Oct 2026 00:00:00 GMT Detta The app you are dictating into keeps focus while Detta works from the menu bar. Check for Updates in the menu, and a notice you will see when a new version is ready. Report a problem from inside Detta. What you wrote is kept if it cannot be sent. Performance improvements and bug fixes. https://www.fermionresearch.com/changelog/#detta-1-0-23 https://www.fermionresearch.com/changelog/#detta-1-0-23 Fri, 02 Oct 2026 00:00:00 GMT Detta Save a file transcription as subtitles, in SRT or WebVTT, or as text with timestamps. Performance improvements and bug fixes. https://www.fermionresearch.com/changelog/#fermion-research-0-2-7 https://www.fermionresearch.com/changelog/#fermion-research-0-2-7 Thu, 01 Oct 2026 00:00:00 GMT Phonon runtime fermion transcribe phonon-2 clip.wav --json returns every word with its start and end in seconds, placed correctly on long audio. fermion serve honours timestamp_granularities, so verbose_json carries words and segments. Both Phonon-2 engines return timings, on Apple silicon and on CPUs. Transcripts are unchanged. https://www.fermionresearch.com/changelog/#fermion-research-0-2-6 https://www.fermionresearch.com/changelog/#fermion-research-0-2-6 Thu, 01 Oct 2026 00:00:00 GMT Phonon runtime fermion serve with a name that is not a published model stops in one line, before any network request. fermion transcribe checks the audio file exists before it loads a model. fermion models and the help texts show each command with its model. https://www.fermionresearch.com/changelog/#fermion-research-0-2-5 https://www.fermionresearch.com/changelog/#fermion-research-0-2-5 Thu, 01 Oct 2026 00:00:00 GMT Phonon runtime The CPU engine reads your processor's features and picks the matching tier, from AVX2, AVX-512 and AMX on x86-64 to dotprod, i8mm and SVE on 64-bit Arm. Raspberry Pi 3 and 4, other Arm boards without dotprod, and x86-64 processors without AVX2 run Phonon-2 on a baseline tier. fermion describe shows the features found, the tier chosen and the binaries loaded, with --json for scripts. https://www.fermionresearch.com/changelog/#fermion-research-0-2-4 https://www.fermionresearch.com/changelog/#fermion-research-0-2-4 Wed, 30 Sep 2026 00:00:00 GMT Phonon runtime Commands name their model, as in fermion transcribe phonon-2 meeting.wav, and phonon, phonon-2 and phonon-1 each run a fixed model. fermion serve takes --unix-socket for an owner-only local socket and --threads for the CPU engine. The CPU and CUDA containers take the model first and keep it in a cache volume. https://www.fermionresearch.com/changelog/#detta-1-0-21 https://www.fermionresearch.com/changelog/#detta-1-0-21 Wed, 30 Sep 2026 00:00:00 GMT Detta Transcribe a File cuts long recordings at natural pauses, so more of every recording comes back as text. Long dictations finish faster. Detta opens at login on new installs. If the speech engine cannot start, Detta says why and lets you copy the details for support. https://www.fermionresearch.com/changelog/#detta-1-0-17 https://www.fermionresearch.com/changelog/#detta-1-0-17 Wed, 30 Sep 2026 00:00:00 GMT Detta Choose any key or key combination as your hold key (1.0.14). Double-tap to lock can use its own key or key combination (1.0.16). Set more than one hold key (1.0.17). https://www.fermionresearch.com/changelog/#detta-1-0 https://www.fermionresearch.com/changelog/#detta-1-0 Tue, 29 Sep 2026 00:00:00 GMT Detta Hold a key and talk. Detta types what you say where your cursor is, in any app, punctuated and capitalised. Phonon-2 runs on the Mac itself, and Detta removes ums, repeated words and false starts. Quick notes keep their recordings, and Transcribe a File turns wav, mp3, m4a, flac, mp4, mov and more into text. Free for Apple silicon Macs, and it keeps itself up to date. https://www.fermionresearch.com/changelog/#phonon-2 https://www.fermionresearch.com/changelog/#phonon-2 Tue, 29 Sep 2026 00:00:00 GMT Models An open English speech recognition model in a 164 MB download, averaging 5.21 % word error on the Open ASR Leaderboard's seven test sets. 174 times realtime through MLX on an M5 MacBook Air, and 143 times on eight Zen 5 cores. fermion-research 0.2.0 makes it the default speech model on Apple silicon and on CPUs across macOS, Linux and Windows, with CPU and CUDA container images. Weights released under CC-BY-4.0. https://www.fermionresearch.com/changelog/#fermion-research-0-1-23 https://www.fermionresearch.com/changelog/#fermion-research-0-1-23 Wed, 02 Sep 2026 00:00:00 GMT Phonon runtime Long recordings are cut into windows at pauses and transcribed in full, from the command line and from the server. --json adds the start and end of each segment, and verbose_json on the server fills segments. https://www.fermionresearch.com/changelog/#phonon-1 https://www.fermionresearch.com/changelog/#phonon-1 Fri, 28 Aug 2026 00:00:00 GMT Models An open English speech recognition model in a 415 MB download that runs on a laptop or a datacenter GPU. It transcribes an hour of audio in about two and a half minutes. Phonon-1 Micro, the smallest model of the family, joins it. https://www.fermionresearch.com/changelog/#neutrino-1 https://www.fermionresearch.com/changelog/#neutrino-1 Mon, 27 Jul 2026 00:00:00 GMT Models Three open-weight language models trained for a compact ternary format. Neutrino-1 8B scores 72.1 on MMLU from a 2.56 GB download. pip install fermion-research runs them on CUDA, Apple silicon and x86, with a local OpenAI-compatible server and a llama.cpp fork. The 0.6B model also serves as the draft for speculative decoding.