v1.3.9.8

v1.3.9.8 Release of the native UI.

Changelog:

• [FEATURE] Add reinit button for plugins
• [FEATURE] Implement OSC Client for typing indication
• [FEATURE] Add Chinese Traditional Translation (AI Translated)
• [TASK] Update translation
• [TASK] Update fyne ui toolkit
• [TASK] Add Chatterbox TTS settings
• [TASK] Change voice list to custom textvalue select widget
• [TASK] Add parakeet v3 model + parakeet estimates
• [BUGFIX] Remove buggy tts switching setting
• [BUGFIX] Remove duplicate translation key

Full Changelog: v1.3.9.6...v1.3.9.8

List of available Plugins: https://github.com/Sharrnah/whispering-plugins/blob/main/README.md

v1.3.9.6

v1.3.9.6 Release of the native UI.

Changelog:

• [TASK] Add "check for update" button in profile window
• [TASK] Add Save profile button
• [BUGFIX] Showing message if port is in use

Full Changelog: v1.3.9.5...v1.3.9.6

List of available Plugins: https://github.com/Sharrnah/whispering-plugins/blob/main/README.md

v1.3.9.5

v1.3.9.5 Release of the native UI.

Changelog:

• [TASK] Add cleanup of toolchain on update
• [TASK] Change language fields for kokoro + zonos tts to use completion field
• [TASK] Change environment paths to use tinycc as compiler
• [TASK] Make initial TTS streamed playback delay configurable
• [BUGFIX] Fix "exec: already started" message

Full Changelog: v1.3.9.3...v1.3.9.5

List of available Plugins: https://github.com/Sharrnah/whispering-plugins/blob/main/README.md

v1.3.9.3

v1.3.9.3 Release of the native UI.

Changelog:

• [FEATURE] Refactor of the Profile window (Should make it more responsive and fix a lot of small bugs)
• [FEATURE] Add window out of bounds check + safe resize
• [TASK] Update dependencies
• [TASK] Make the user error reporting more robust
• [TASK] Improve finding profile directory
• [TASK] Improve logging formatting on loading from history
• [TASK] Update to go 1.25 + Update dependencies
• [TASK] Add tts queue setting
• [TASK] Add environment variables for new toolchain tools
• [TASK] Improvement for environment variables building
• [TASK] Update translations
• [TASK] Add setting for microphone passthrough
• [TASK] Add internal osc_force_activity_indication setting
• [TASK] Save and load tts special settings (like emotions for zonos)
• [BUGFIX] Set progress to 0 if its negative
• [BUGFIX] possible race condition on audio device switching
• [BUGFIX] Log length slowdown
• [BUGFIX] Loading state showing multiple labels with same text
• [BUGFIX] Fix some thread ui call warnings
• [BUGFIX] AI Model estimate for Voxtral
• [BUGFIX] Crash on audio API switch
• [BUGFIX] Improve python multiprocess handling on exit

Full Changelog: v1.3.8.4...v1.3.9.3

List of available Plugins: https://github.com/Sharrnah/whispering-plugins/blob/main/README.md

v1.3.8.4 (Maintenance release)

v1.3.8.4 Release of the native UI.

Changelog:

• [BUGFIX] Infinite progress bars no longer multiply infinitely for downloads with unknown size ♾️
• [BUGFIX] Crash if unavailable option preselected
• [BUGFIX] Base filter breaking user filter

Full Changelog: v1.3.8.3...v1.3.8.4

List of available Plugins: https://github.com/Sharrnah/whispering-plugins/blob/main/README.md

v1.3.8.3

v1.3.8.3 Release of the native UI.

Changelog:

• [FEATURE] Add plugin settings reset function.
• [FEATURE] Rework UI to be single-threaded
• [FEATURE] Add Voxtral ui elements
• [TASK] Update Chinese translation (thanks to Matcha)
• [TASK] Update dependencies
• [TASK] Rework logs window (LogText widget)
• [TASK] Change displaying plugin gifs to only animate on hover
• [TASK] Add new Nemo Canary models options (1b, 180m-flash, 1b-flash)
• [TASK] Add option to enable file logging on run.
• [TASK] Add Txt_translate_realtime_sync setting (unifies realtime settings between STT and Text-Translation)
• [TASK] Adds Orpheus TTS, Parakeet and Large v3.5 Distilled model options
• [TASK] Add option to hide "hide" button on required downloads
• [TASK] Rename the Quit running process button.
• [TASK] Add option to open log in new window
• [TASK] Detect if app is run from temp directory
• [TASK] Detect free space
• [TASK] Improve completion widget filter
• [TASK] Improve multimodal handlin in profile settings
• [TASK] More robust exiting of zombie backend process
• [BUGFIX] Add missing translations
• [BUGFIX] Quit app on closing profile window
• [BUGFIX] Try to improve audio initialization
• [BUGFIX] Nullpointer exception if non-existing element is selected
• [BUGFIX] Handling of temporary profiles and existing profiles with same name
• [BUGFIX] Creating new profile crash while in-memory profile is selected
• [BUGFIX] Disable AI device and precision selects for disabled OCR type
• [BUGFIX] Submit new value on voxtral language fallback in translate mode

Full Changelog: v1.3.7.2...v1.3.8.3

List of available Plugins: https://github.com/Sharrnah/whispering-plugins/blob/main/README.md

1.3.8.1-beta (CUDA 12.8)

This is a Beta version since NVIDIA 50x Series Blackwell GPU's require CUDA 12.8.

This beta release has the same features as v.1.3.7.2 but downloads the Python backend with the nightly Pytorch 2.7.0 version and CUDA 12.8.1

You might need the newest CUDA-Toolkit installed as well: https://developer.nvidia.com/cuda-downloads

This should also work with older NVIDIA GPU's.
Please let me know if you encounter any issues.

v1.3.7.2

v1.3.7.2 Release of the native UI.

Changelog:

• [FEATURE] Show addidional translations in auto translate checkbox label
• [FEATURE] Add error logging
• [FEATURE] Add Clear Transcriptions button
• [TASK] Separate MessageSend Channel from Fields module
• [TASK] Improve CompletionEntry widget
• [TASK] Add Plugin support for select_textvalue and select_completion widgets
• [TASK] Improve logging and UX
• [TASK] Replace infinite progress bar with Activity widget
• [TASK] Add Streamed playback, Zonos TTS, Phi-4 and Kokoro model settings
• [TASK] Add OCR type setting
• [TASK] Improve AI model memory consumption estimate logic
• [BUGFIX] Add missing OSC Sync setting translations
• [BUGFIX] Only resetting realtime label timer OR processing timer.
• [BUGFIX] Always set AI related env variables
• [BUGFIX] single model ocr type language detection
• [BUGFIX] Calculate memory if model has no specified model size (single sized models)
• [BUGFIX] Make sure only 1 download per file is running

Full Changelog: v1.3.6.1...v1.3.7.2

List of available Plugins: https://github.com/Sharrnah/whispering-plugins/blob/main/README.md

v1.3.6.1

v1.3.6.1 Release of the native UI.

Changelog:

• [FEATURE] Add option to reorder additional language translations
• [FEATURE] Add markdown parsing for Plugin List.
• [FEATURE] Add "Export Last Generation" to TTS Tab
• [TASK] Improve handling of deactivated VAD settings
• [TASK] Add language_detection_on_each_segment setting
• [TASK] Improve backend restart logic
• [TASK] Improve main window recognition for dialog parenting
• [TASK] Remove obsolete validation of Transcript/Translate textareas
• [TASK] Remove DirectSound API from list (Python backend seems incompatible with DirectSound anyway)
• [TASK] Reimplement websocket message read limit
• [TASK] Improve list seperator style
• [BUGFIX] Crash on switching TTS Type in Settings tab of main UI window.
• [BUGFIX] Only show notification of wrong setting combination when changing it after initial profile loading.
• [BUGFIX] TextValueSelect widget invalid defaultIndex error

Full Changelog: v1.3.5.1...v1.3.6.1

List of available Plugins: https://github.com/Sharrnah/whispering-plugins/blob/main/README.md