Skip to content
Try MeetVoice

What's New

v1.6.1 June 5, 2026

  • Fixed macOS update installs: downloaded DMGs no longer show "disk image damaged" when you open them.
  • More reliable multilingual meetings with your own API keys: multilingual sessions now use the same translation fallback as single-language mode, and subtitles are less likely to drop after language switches.
  • Smoother first-time setup: the welcome tab no longer reopens every time you open the extension popup, and setup progress and final hints are fully localized in all supported languages.
  • Trial starts correctly from the desktop app: choosing "Try for free" on a fresh install now properly begins your trial and starts the local server.
  • More reliable session start: starting translation from the popup works better when the desktop connection URL is still being discovered.

v1.6.0 June 3, 2026

  • Live Edge voice updates: changing the voice now applies during the meeting without restarting the session, so you can adjust the sound more naturally.
  • Safer extension settings: Deepgram keys, glossary entries, subtitle preferences, and connection options are saved more carefully and are less likely to reset or break a working setup.
  • More reliable transcript exports: downloads handle edge cases more safely, so long meetings and unusual transcript content are less likely to produce broken files.
  • Clearer desktop update experience: the app explains update status and next steps more plainly, making it easier to know when MeetVoice is ready.
  • Sturdier background work: the local server, translation proxy, and website analytics checks now handle startup, shutdown, and failed requests more gracefully.

v1.5.9 June 1, 2026

  • More accurate multilingual meetings: when participants speak different languages, MeetVoice now recognizes each person's language more accurately and mixes languages up less in the subtitles — even when someone switches language mid-sentence. Fewer mistranslated lines and faster, steadier subtitles.
  • Steadier language detection: short replies and the occasional foreign word are handled more accurately, so the subtitle language no longer flickers on individual words.
  • Simpler connection settings: the local server URL is hidden by default, manual mode is available only when needed, and there is less risk of accidentally breaking settings that already work.
  • Helpful popup tooltips: short explanations near multilingual mode clarify when to choose one primary language, several languages, or auto-detection.

v1.5.8 May 27, 2026

  • The glossary is smarter: MeetVoice now suggests words and names that speech recognition was not fully sure about, so you can quickly add them to the glossary and improve accuracy in the next phrases.
  • Auto-added participant names are easier to understand: the extension window shows how many names are already used for the current meeting, and the hint appears only during an active session.
  • New quick presets for work meetings: add basic terms for Tech and Finance with one click — less manual setup before a call.

v1.5.7 May 23, 2026

  • Status dashboard in the desktop app (Windows): open it from the tray icon to see whether the server is running, check your license or trial, manage updates, and jump to the website, Chrome extension, or Deepgram console.
  • First-time setup checklist in the desktop app: at a glance you can see whether the extension is connected, a Deepgram key is saved, and you have opened a Google Meet call.
  • Flexible updates on Windows: choose semi-automatic update checks or manual-only — fewer surprise restarts during an active meeting.

v1.5.6 May 22, 2026

  • Separate voices for incoming and outgoing translation. Settings now has two independent voice pickers: one for what you hear (the voice translating your counterpart), one for what meeting participants hear from you. Configured per language.
  • Improved speaker name detection. Several bugs fixed where speaker names in the transcript appeared incorrectly or were missing. Names now appear faster and more accurately, especially for short utterances and at the start of a call.
  • Better translation for similar language pairs. Translation quality improved for Ukrainian↔Russian, Portuguese↔Spanish, Dutch↔German and other close pairs — fewer literal translations, more natural phrasing.
  • API keys stored in the OS secure vault. Deepgram and other keys are now encrypted via the Windows/macOS system keychain instead of being stored in plain text.
  • Transcript button moved to the right side of the screen — no longer overlaps Google Meet controls.

v1.5.5 May 20, 2026

  • Mixed-script subtitles: when a phrase in the source language (for example, English) includes names in another script — "Alexandr and Serhiy will join..." — the translation is no longer dropped due to a false SKIP. Previously such lines sometimes never appeared on screen even though they still needed to be translated.
  • Stronger protection for the automatic name glossary from Meet: harmful or accidental snippets such as "System:" / "User:" in a participant's display name are filtered further before they reach the translator, so one person's renamed label is less likely to affect subtitles for the whole meeting.

v1.5.4 May 17, 2026

  • Participant names are now preserved verbatim across translation: if your colleague's name is "Maciej", they stay "Maciej" in the Russian transcript instead of becoming "Мацей". This applies to all 18 languages — Latin, Cyrillic and CJK scripts are now passed through letter-for-letter via the automatic glossary. Searching for a colleague by name in subtitles, meeting history and SRT/TXT exports now works the same on both sides of the call.
  • Subtitle stability in real time: the extension now correctly translates speech fragments and disfluencies ("so, like, basically...", "um, the thing is..."), no longer treating them as technical noise. Previously such fragments would sometimes disappear from the overlay or get padded with words nobody actually said. Especially noticeable during rapid back-and-forth and mid-sentence corrections in dialogue.
  • AI summary reliability (premium feature): meeting summaries are now consistently produced even when the transcript mentions a product name in quotes ("Your data. Your dashboard."), participant quotes, or code in backticks. Previously these fragments broke the response structure and the summary wasn't saved. Summaries in German, Hungarian and Korean have also become more stable.
  • Translator and summary protection against content tampering attempts: added extra filtering layers for incoming data (Meet participant names, recognised speech, transcript content) so that accidental or deliberate manipulation by individual participants doesn't affect translation and summary quality for the rest of the group. Especially important for meetings with many participants or open webinars.

v1.5.3 May 15, 2026

  • Multilingual meetings: MeetVoice now works on calls where participants speak different languages. The extension automatically detects each speaker's language and translates everything to yours — no need to switch settings during the meeting. A colored language badge next to the speaker's name appears in subtitles and meeting history, and PDF, SRT and TXT exports show the source language of each line
  • Active-language legend in subtitles: in multilingual meeting mode, a compact strip above the subtitles shows the languages the extension is listening to. Each chip uses the same color as the badge next to the speaker's name, so at a glance you see which languages are being monitored and which one is being spoken right now
  • API Keys settings made clearer: a tier overview at the top shows what each key unlocks (speech recognition, faster translation, premium voices), with colored dots that turn green as you configure them. Under each field, a live hint explains the current state — what works without the key and what you gain by adding it. Groq and OpenAI translation keys are now stored separately, so switching providers no longer mixes them up. For OpenAI users: a «Use translation key» button copies the key into the voices field with one click
  • Participant names are now added to the translation glossary automatically. Translations stay consistent across the whole call — «Aleksey» no longer drifts between «Alex», «Aleksei» and «Alexey». Your manually entered glossary entries retain priority when the 500-character budget is full.
  • First-install setup guide: a welcome page now opens automatically when you install MeetVoice for the first time, walking you through the two setup steps — installing the desktop application and adding your Deepgram API key. In the panel, a clear 2-step checklist replaces the old single-line warning, showing live status of both prerequisites and auto-collapsing when you're done.

v1.5.2 May 7, 2026

  • Translation auto-recovery on invalid API key: if your Groq or OpenAI key stops working mid-session (expired, revoked, or mistyped), translation now seamlessly falls back to the built-in proxy for the rest of the meeting instead of failing every phrase. You'll still see a notification so you know to fix the key, but the meeting keeps going without interruption
  • Quick links to obtain API keys: every key field in Settings → API Keys (Deepgram, Groq, OpenAI, OpenAI TTS) now has a «Get key →» link that opens the provider's console in a new tab — no more hunting for the right URL

v1.5.1 May 3, 2026

  • Bilingual AI summary now generates correctly in all 18 languages — previously a Bulgarian, Czech, Polish or similar summary block fell back to English text with an «AI Summary» heading even though the meeting was in that language. PDF section titles («Key Decisions», «Action Items», «Topics Discussed») are now also localized for every supported language
  • Refined data flow disclosure in API keys settings: keys are sent only to provider APIs (Deepgram, OpenAI, Groq), never to MeetVoice servers. The same precision now reflected in the privacy policy on the website

v1.5.0 May 1, 2026

  • Keyboard shortcuts inside Meet: Alt+T toggles translation, Alt+S hides or shows subtitles, Alt+M instantly mutes TTS — control your session without taking your hands off the keyboard or opening the panel mid-presentation
  • Meeting glossary in Settings — add coworker names, product names and technical terms (up to 500 chars), and the translator handles your specific vocabulary noticeably more accurately. Persists between sessions
  • Transcript export to SRT and TXT alongside PDF — SRT for subtitle editors (Premiere, DaVinci, Subtitle Edit), TXT for quick pasting into chat or email
  • AI meeting summary now works in all 18 languages — Polish, Dutch, Turkish, Japanese, Korean, Czech, Slovak, Hungarian, Romanian and Bulgarian previously failed with «Invalid language». Summaries now generate in any supported language
  • 5-minute trial-ending notification with a direct link to license activation — no more sudden cutoffs mid-call
  • More resilient PDF export: fixed overlapping cards in Japanese and Korean transcripts, added a safeguard against crashes on extra-long meetings (>500 phrases) by trimming to the most recent entries

v1.4.9 April 29, 2026

  • Translation now auto-stops after 15 minutes of silence — protects your battery, transcription credits, and trial budget if you forget to disable it after a call
  • Clearer 'Activate a license' prompt when your trial ends mid-session, with the message localized in all 18 supported languages

v1.4.8 April 28, 2026

  • Added 5 new languages: Czech, Slovak, Hungarian, Romanian, Bulgarian
  • Popup, subtitles, TTS and website now available in all 18 languages

v1.4.7 April 20, 2026

  • Added 5 new languages: Polish, Dutch, Turkish, Japanese, Korean
  • Popup, subtitles and website now available in all 13 languages
  • Auto-retry on translation rate limits — if Groq throttles, MeetVoice silently falls back to OpenAI so translation keeps flowing
  • CJK subtitle rendering improvements: Japanese line-break and mid-stream sentence splitting for smoother Asian-language flow

v1.4.6 April 16, 2026

  • Added 4 new languages: Spanish, Portuguese, French, Italian
  • Popup, subtitles and website now available in all 8 languages

v1.4.5 April 12, 2026

  • Fixed speaker detection in 1-on-1 calls — names now appear correctly even with just two participants
  • Microphone off? The app no longer wastes resources processing silent audio
  • Fixed a rare update notification error that could appear on app startup
  • Internal cleanup to comply with Chrome Web Store review requirements

v1.4.4 April 10, 2026

  • Subtitles now wrap long phrases into balanced, easy-to-read lines instead of one long string
  • Subtitle font size automatically adapts to your window size — no more tiny text on small screens or oversized text on ultrawide monitors
  • Fixed speaker name detection after a recent Google Meet interface update — names appear reliably again in group calls
  • Fixed AI meeting summary not generating when using the desktop application
  • Improved stability: resolved several timing issues that could cause brief audio glitches or subtitle flicker during long meetings

v1.4.3 April 9, 2026

  • AI meeting summary now written natively in BOTH meeting languages at once — no more one-sided or machine-translated versions, each summary is crafted directly by the model in its own language
  • Your PDF export now shows two clean sections back-to-back — one per language with native headings and polished formatting
  • If one language hiccups, you still get the other one instantly plus a clear heads-up toast — no more all-or-nothing summaries
  • Single-language meetings stay just as fast and lightweight — zero extra cost when both sides speak the same language
  • Smarter error messages when summary generation fails — you'll finally know whether it's a server hiccup or an API key issue
  • Deep security audit: tighter validation on all server messages, stronger API key handling, and hardened translation pipeline
  • Fixed: speaker names in group calls could sometimes resolve incorrectly due to a missing internal message relay
  • OpenAI TTS key test button no longer consumes API credits — uses a lightweight check instead
  • Mistyped license key? You can retry in 10 minutes instead of waiting a full hour

v1.4.2 April 9, 2026

  • Speaker names in group calls (3+ people) appear from the very first phrase — no more 30-second warm-up
  • Wrong name guessed early? We fix it retroactively on all previous subtitle cards once the real speaker is known
  • New presenter mode — much faster recognition for webinars and lectures with a single dominant speaker
  • Fewer flickering labels — names only update when we're confident, no more twitchy back-and-forth on short phrases
  • Fixed: speaker name corrections stopped working after waking a Meet tab from Chrome's back-forward cache

v1.4.1 April 8, 2026

  • Fresh new look — wider extension panel, brand-colored layout, bigger buttons and a polished overall feel
  • Turn on 'Speak my translation aloud' before you even join a meeting — no more flipping switches mid-call
  • Cleaner volume controls — each slider now has a clear label so you know which audio channel you're adjusting
  • Settings reorganized into four easy-to-browse sections: Voice, Subtitles, API Keys and Advanced — with a 'Setup required' hint when keys are missing
  • Voice picker now uses compact play and reset icons — long voice names finally fit, and the preview button shows what it's doing
  • Meeting history is easier to navigate with keyboard, and you see a loading placeholder instead of a blank screen
  • Extension now starts in your browser's language automatically (Russian, Ukrainian, English or German)
  • Better readability everywhere — stronger contrast on text, borders and dividers

v1.4.0 April 8, 2026

  • Your voice is no longer almost inaudible while the translation plays — by default you now stay audible at 20% volume, so your peer can still hear you speak naturally behind the translation
  • New slider in the panel lets you fine-tune exactly how quiet your voice gets during translation — from barely audible (10%) to no quieting at all (100%). Find it right under the Translation volume slider when outgoing translation is enabled

v1.3.9 April 7, 2026

  • Pick a specific voice for each language — choose from the full neural voice catalog (English, German, Russian, Ukrainian) instead of just male or female
  • Preview any voice in Settings before starting a meeting — hear exactly how it sounds in one click
  • Your voice picks are remembered across sessions and survive reconnects
  • Reset to default voice anytime — one button per language

v1.3.8 April 7, 2026

  • Test your API keys in one click — check Deepgram, translation and TTS keys directly from Settings
  • Mute translation voice with a single tap — keep subtitles visible while silencing the TTS
  • More accurate speaker names in group calls with 3 or more participants
  • Clearer error messages — when something goes wrong, you'll see exactly what to fix and where, in your language
  • Improved reliability and security under the hood

v1.3.7 April 4, 2026

  • Added protection against selecting the same language for both sides
  • Enhanced connection security — stricter message validation
  • Fixed: empty API keys in settings no longer cause connection errors

v1.3.6 April 3, 2026

  • Fixed voice overlap — consecutive translations no longer play over each other
  • Improved speaker name detection — works in large meetings, late joins, and 16 UI languages
  • Faster voice response time
  • Improved PDF export reliability

v1.3.5 April 3, 2026

  • AI meeting summary — one-click summary of your entire meeting
  • German language support (Deutsch) — UI, subtitles, and voice
  • Improved PDF export — faster generation, cleaner layout
  • Pulse indicator on transcript button while recording
  • Fixed: meeting transcript now saved when session ends unexpectedly (trial expired or connection lost)
  • Fixed: failed connection attempt no longer creates empty entry in meeting history
  • Improved voice stability — fixed audio cutoff on consecutive speech segments
  • Enhanced security and stability

v1.3.4 March 31, 2026

  • Faster voice response — reduced TTS latency
  • Deepgram auto-reconnect now stops on invalid API key
  • Fixed audio resources not cleaned up on mic switch in Meet
  • Fixed transcript buffer overflow on very long meetings

v1.3.3 March 30, 2026

  • Meeting transcript — real-time panel with speaker names and timestamps
  • Export transcript to styled PDF with speaker color coding
  • Meeting history — browse and manage up to 50 past meetings
  • Fixed meeting time display (now uses your local time)
  • All 4 languages available as user or peer language

v1.3.2 March 26, 2026

  • Secure connection required for remote servers (wss://)
  • Fixed meeting audio staying quiet after empty translation
  • Faster audio processing with zero-copy data transfer
  • Better error messages — no more confusing technical details
  • Improved Telegram bot protection against spam
  • Fixed date display on Download page for different timezones
  • Settings labels now fully translated in RU/UK

v1.3.1 March 26, 2026

  • Fixed meeting audio staying muted after translation error or reconnect
  • Improved stability on unstable connections
  • Enhanced desktop application license window security
  • Faster translation processing via cloud proxy

v1.3.0 March 25, 2026

  • Built-in translation — only 1 key needed (Deepgram)
  • Translation and voice work automatically, no extra setup
  • Simplified settings with collapsible advanced section
  • Subtitles now appear at the top by default

v1.2.0 March 24, 2026

  • Free built-in voice — no OpenAI API key needed for speech
  • Only 2 API keys required now (Deepgram + Groq) instead of 3
  • Male/Female voice toggle
  • OpenAI TTS available as optional upgrade
  • Faster voice response time

v1.1.0 March 20, 2026

  • Added BYOK (Bring Your Own Keys) support
  • Added UI localization (RU/UK/EN)
  • Improved TranscriptBuffer with smart endpointing

v1.0.0 March 16, 2026

  • Initial release: bidirectional EN/DE ↔ RU/UK translation
  • Desktop app for Windows and macOS
  • Chrome extension with subtitles and TTS