TypeWhisper 1.8.1 Release Candidate 2

The second release candidate for TypeWhisper 1.8.1. It contains everything in RC1 plus the changes below, merged since v1.8.1-rc1.

Highlights

• Canary and Cohere Transcribe (Local) no longer stop with an error under Auto-detect all languages when nothing picks the language, for example when the Language Detection plugin is unsure on a short dictation, is not enabled, or hears a language the engine does not support. They now use the first of your preferred languages in System Settings > General > Language & Region that they support, and only stop with the error when they support none of them. Google Cloud STT 1.1.1 keeps using its default language code in these cases.
• Granite Speech adds IBM's Granite Speech 5.0 models. Granite 5.0 TurboCTC (470M, about 950 MB) is the new default: it transcribes English, French, German, Spanish, Portuguese, Italian and Japanese with punctuation and capitalization in a few milliseconds per sentence, but cannot translate or use dictionary terms. Granite 5.0 2B (about 4.6 GB) also writes punctuated text, translates and uses your dictionary terms. If you already use a Granite 4.0 model, it stays selected.
• Granite's Translate lets you choose the target language in the Recorder, file transcription and dictation recovery: English, French, German, Spanish, Portuguese, Japanese, Italian or Chinese. English is the default. Until now Granite translated into the selected spoken language, so German speech with German selected came back in German although the task said Translate to English.

Dictation

• Dictating into GNU Emacs, a remote desktop client such as Parsec, or a new message in Apple Mail no longer ends with "No text field detected". These apps either report only their window to Accessibility or do not show their text changing, so TypeWhisper no longer takes that as a missed text field. Web pages without a text field still get the warning.
• Chinese, Japanese and other languages written without spaces are counted by characters for the "Skip AI post-processing" word threshold, History and Statistics. Until now, Chinese dictations always skipped AI processing, no matter how long they were.

Recorder and file transcription

• Deleting a recording asks first and moves the audio and its sidecar files to the Trash instead of deleting them for good.
• Translate is offered only for models that can translate. A Translate choice made for an earlier model no longer makes every file fail after you switch to a model that cannot translate.

Plugins and SDK

• Parakeet 1.6.1: Using another Parakeet model for a single transcription, as the local API's model, the CLI's --model or a workflow with its own Parakeet model do, now waits for that model to load. Until now it failed with "Cloud provider not configured. Please set an API key." Nemotron 3.5 ASR Streaming no longer drops the first and last words of files and other recordings it transcribes after they end; live dictation stays as fast as before.
• Granite Speech 1.2.0 (see Highlights). Translation also works while dictionary terms are active; the terms are now passed as keywords after the instruction, as the model expects. The local API's target_language with task=translate goes straight to Granite when it supports that language.
• Canary 1.1.1, Qwen3 1.1.15, Voxtral 1.0.20 and Local LLM (MLX) 1.0.7: Each of these plugins brings its own copy of Apple's MLX framework. With several of them enabled, one plugin could run code from another plugin's copy, which can crash TypeWhisper during a transcription or text processing. Each plugin now uses only its own copy, as Granite Speech already does.
• Google Cloud STT 1.1.1 declares that it has its own default language, so the new fallback to your preferred languages does not apply to it.
• Plugin SDK: engines can report translation support, translation target languages and dictionary term support per model through the Objective-C runtime (supportsTranslationForModelId:, translationTargetLanguagesForModelId:, supportsDictionaryTermsForModelId:), as they already can for supported languages. The host uses them for per-flow model overrides and enforced models.

Compatibility and updates

Requires macOS 14 or later; supports Apple silicon and Intel Macs. The iCloud bridge is included in every release.

Parakeet 1.6.1, Canary 1.1.1, Language Detection 1.0.0, Cohere Transcribe 1.1.0 and Google Cloud STT 1.1.1 require TypeWhisper 1.8.1. Granite Speech 1.2.0, Qwen3 1.1.15, Voxtral 1.0.20 and Local LLM (MLX) 1.0.7 also run on TypeWhisper 1.8.0; the target language choice for Granite needs this release.

RC2 is available through GitHub and the Release Candidate update channel. The stable release and Homebrew remain on 1.8.0. Please report regressions with the release tag, macOS version, and the affected engine or plugin.