TGSpeechBox vs WayFinder

TGSpeechBox is a high-quality speech synthesizer that works as a system voice with VoiceOver and as a standalone text-to-speech app. Features: • 26 languages with natural-sounding speech • Full VoiceOver integration — use as your primary system voice • 7 voice presets plus YAML-defined voice profiles • Deep engine tuning: pitch mode, voice tone, formant sharpness, inflection, tremor, breathiness, and more • Phoneme editor: fine-tune individual speech sounds with live preview • Pronunciation dictionary: add custom word pronunciations with IPA override support • Stress, compound, and character dictionaries for advanced control • Export and share your customizations • Adjustable sample rate (11025–44100 Hz) • Rate override and rate boost for VoiceOver • Language lock: keep your preferred language regardless of system setting • Runs entirely on-device — no internet required, no data leaves your phone TGSpeechBox uses a Klatt-style formant synthesis engine with eSpeak-ng for phoneme generation. It is open source under the MIT license. Built by a blind developer, designed for accessibility from day one.

WayFinder is a voice-first visual assistant for blind and low-vision people. Press the microphone, ask a question aloud, and WayFinder takes one photo and speaks an AI-generated description. Ask about objects, text, colors, or the general scene in front of the camera. HOW IT WORKS • Sign in with Apple, with Google, or with an email address and password. Nothing else is asked of you. • Press the microphone to speak. That is the only way WayFinder listens — there is no wake word and no background listening. • You choose whether to send camera images for third-party AI processing. Until you agree, no image is sent. You can change the decision in Settings. • Each request uses one still photo. WayFinder does not record video. • Speech recognition runs on the iPhone. Raw microphone audio is not sent to WayFinder. • Answers and important status messages are spoken aloud. Controls have VoiceOver labels, large touch targets, and scalable text. SAFETY LIMITS AI can miss, misidentify, or misread things. If WayFinder cannot produce a sufficiently grounded answer, or if the camera, network, account, server, or AI provider fails, it tells you to stop instead of presenting the failure as a clear path. WayFinder is assistive information only. It is not a mobility aid or a medical device. It does not replace a white cane, guide dog, your own judgment, or orientation-and-mobility training. Never rely on it to decide whether to step or cross. USAGE LIMIT Each authenticated account receives exactly 25 lifetime successful vision analyses. Request 26 and later is refused before any AI request is made. There is no subscription, payment, purchase, upgrade, or quota reset. PRIVACY AND CONTROL The requested photo is sent over an encrypted connection to the WayFinder server and processed by a Google Gemini model on Google Cloud Vertex AI. WayFinder does not store the raw image. Questions, answers, and any answer report you submit are retained for up to 30 days for history and service operation. You can erase history or delete your account in the app. LANGUAGES The interface and spoken flow support English and Russian.