azVoxtrans

Turn what you say into text — and turn entire recordings and videos into text too. azVoxtrans does speech recognition entirely on-device: no network needed, low latency. While it listens, it also records the raw audio, so you can play it back later to check exactly what was said. ■ Real-time speech-to-text Tap to start recording and see results appear as you speak. Pausing mid-sentence won’t cut you off or clear what’s already been recognized — tap again and it keeps appending. Text only disappears when you tap “Clear.” ■ Full transcription of long recordings and video (Pro) Lectures, meetings, interviews, videos — transcribe the whole thing with no length limit. Import from Files or your photo library; audio is automatically extracted from video. ■ Translation: online and on-device, side by side Transcripts can be translated directly. On-device translation is free, offline, and never leaves your phone — it’s the default. For better quality, add your own API key from a translation provider to switch to online translation. Your key stays on this device only, we never see it, and any usage cost is settled directly between you and that provider. The translation never overwrites the original — both stay visible and can be copied separately. ■ Recording scenes for every situation Three built-in scenes: Personal, Lecture, and Interview. Different distances need different pickup patterns: Personal is close, handheld use; Lecture switches to a cardioid pattern with boosted gain to pick up a speaker several meters away; Interview suppresses ambient noise and works well with an external or Bluetooth mic. ■ Tuning: adjust it yourself, then listen and decide (Pro) When the built-in scenes aren’t quite right, open up gain, noise gate, low-cut filter, and directionality and adjust them yourself. Tap “Test” to record a short sample (up to 30 seconds), then play it back — you’re hearing the same clip with your current settings applied. Change one setting, listen again, and compare directly instead of guessing. Save what you land on as your own recording scene, and it shows up alongside the three built-in ones for next time. ■ Playback and read-aloud Playback replays your original recording; read-aloud uses synthesized speech to read the text in the text box out loud. Each read-aloud generates a new audio file you can save or share. ■ Export and share Text files, recording audio, and read-aloud audio can all be saved to the Files app or shared directly to other apps. ■ Interface language and working language, set separately 10 interface languages; the working language (for recognition and read-aloud) can be switched independently — an English interface with a Chinese working language works fine. ■ Free vs. Pro The free version includes real-time speech-to-text (up to 8 minutes per session); you need to tap “Clear” after each session before recording again. Pro unlocks: ・Unlimited recording time ・Full transcription of long recordings and video (no length limit) ・Translation ・Tuning and custom recording scenes ・Playback of original recordings ・File export and document import Plans and pricing follow the live store price shown on the in-app paywall. After switching devices or reinstalling, tap “Restore Purchases” to reactivate. Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/ Supports iPhone and iPad.