{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreida4o2xmokmnb7vkzm7qxx2go5q5efm3mz3gjvkbrpc2coreolxmm",
    "uri": "at://did:plc:mz7h4r2iyp2egghuqaolnsev/app.bsky.feed.post/3mircazlaaob2"
  },
  "path": "/apps/ios/utilities/tgspeechbox",
  "publishedAt": "2026-04-05T12:18:08.000Z",
  "site": "https://applevis.com",
  "textContent": "A formant-based speech engine great for reading text at high speech rates in 26 languages. Built by a community of testers who improve each release.\n\nTGSpeechBox is a high-quality speech synthesizer that works as a system voice with VoiceOver and as a standalone text-to-speech app.\nFeatures:\n• 26 languages with natural-sounding speech\n• Full VoiceOver integration — use as your primary system voice\n• 7 voice presets plus YAML-defined voice profiles\n• Deep engine tuning: pitch mode, voice tone, formant sharpness, inflection, tremor, breathiness, and more\n• Phoneme editor: fine-tune individual speech sounds with live preview\n• Pronunciation dictionary: add custom word pronunciations with IPA override support\n• Stress, compound, and character dictionaries for advanced control\n• Export and share your customizations\n• Adjustable sample rate (11025–44100 Hz)\n• Rate override and rate boost for VoiceOver\n• Language lock: keep your preferred language regardless of system setting\n• Runs entirely on-device — no internet required, no data leaves your phone\nTGSpeechBox uses a Klatt-style formant synthesis engine with eSpeak-ng for phoneme generation. It is open source under the MIT license.\nBuilt by a blind developer, designed for accessibility from day one.",
  "title": "TGSpeechBox"
}