Dictate 5.0.0

Dictate 5.0.0 is the biggest update since 4.0 — the first time you open the app after updating, a new What's-new tour walks you through the highlights and drops you straight into each setting.

⌨️ Keyboard & typing

• Glide typing — swipe across the keys to type whole words, with per-language dictionaries that download on demand. (#127)
• Word suggestions, spell check & autocorrect — on by default, with SwiftKey/Gboard-style ranking (keyboard-proximity noisy-channel + bigram context across 34 languages). (#127)
• Gboard-style autocorrect UX — the auto-applied candidate is bolded and the word you actually typed stays tappable in the suggestion strip, so one tap undoes a correction. (#150)
• Classic keyboard-less "legacy" dictation layout — the pure voice screen from Dictate 3 is back: set it as your default (locked) or keep it a horizontal swipe away from the full keyboard, with number-pad + system-emoji overlays, space-swipe cursor movement and hold-backspace multi-character selection. (#125)
• Bigger emojis with tighter spacing (#148), Select-all is now a toggle that reflects the field's selection (#152), a new high-contrast E-Reader / E-Ink theme (#54), and accent auto-contrast (black text/icons on very light accent colours).

🎙️ Transcription & AI

• Real-time / streaming transcription — watch your words appear as you speak, with OpenAI, Deepgram, Soniox, AssemblyAI and ElevenLabs, including an experimental live preview even on the floating button. (#128)
• Three new cloud providers — ElevenLabs Scribe, Deepgram and AssemblyAI; OpenRouter now auto-discovers dedicated STT models. (#143, #157)
• Offline transcription — the on-device NVIDIA Parakeet TDT 0.6B model (experimental) runs with no internet and nothing leaving your phone, and a local Silero VAD silence filter skips empty recordings so you never get ghost text or waste an API call. (#154, #93)
• Reasoning-effort control for rewording calls — globally (#141) and per prompt (#155).

📚 Prompts & community

• Community prompt library — browse rewording prompts shared by others and install them in a tap, or contribute your own. (#105)

📊 Insights & feedback

• Dictation statistics — a stats screen, a home-screen card and milestones. (#142)
• Optional haptic feedback for the recording / transcribing / rewording states — on the phone and on Wear OS. (#166)

🎈 Floating button

• Far more reliable keyboard-style text insertion plus resend-on-failure, a fully custom colour, and a live realtime preview. (#156, #160, #161)

⚙️ Settings & compatibility

• Dictate settings reorganised into a scannable category hub. (#153)
• Selectable audio input source, including the new high-priority VOICE_COMMUNICATION option that keeps working when another app is holding the mic. (#62, #167)
• Trust user-installed CA certificates (#137); Ollama / self-hosted servers now allow cleartext HTTP with an editable base URL (#136).
• Instant recording can skip number-only fields (#146); Dictate offers to save the recording when a transcription fails as too large (#144).
• In-app language-data attributions (Settings → About).

⚡ Performance & fixes

• Fixed typing jank (especially on Samsung): the floating-button accessibility service no longer re-fetches the entire focused node tree on every keystroke.
• Audio-pipeline speedups: streaming Base64 encoding, a PCM resampler fast path, and fewer capture-buffer copies.
• The mic now stops when the screen turns off mid-recording. (#147)
• Crash fixes: the shared prompts database was being closed per query (#138), and an invalid inline-suggestion inflate size (#145).
• Auto-formatting no longer spills its prompt into the field on empty recognition (#124); the "keyboard not enabled" banner no longer flashes on settings open.