Home › Utilities
US
1 of 1 storefronts
Content in en-US
Content in en-US
Information
Preview 3 platforms
iPhone 2 images
iPad 1 image
Mac 3 images
What’s New Version 3.0.1
This version adds many new features:
- Higher cascade formants F7 (6500 Hz) and F8 (7500 Hz) for spectral presence above F6 (Rabiner 1968 defaults). Nyquist-proximity fade auto-mutes them at low sample rates.
- Parallel F7/F8 resonators for fricative high-frequency presence (amp 0.15/0.07).
- 2x source oversampling for cleaner harmonics at lower sample rates.
- Dual-oscillator chorus for vocal fold asymmetry (VoicingTone V5): chorus depth and variation sliders for natural vocal fold jitter.
- Brown noise aspiration blend: white/brown noise mix by sample rate (44k=100% white, 22k=70/30, 16k=50/50). Fixes aspiration thinness at lower sample rates.
- Glottal sharpness rebalanced for F7/F8 spectral dynamics.
- Transition bandwidth widening after obstruents: decaying BW boost across first 3 micro-frames, scaled by F2 sweep width.
- Word-final stop audibility improved: stop floor 4ms to 6ms, word-final bonus 5ms to 8ms, voiced alveolar softening eased.
- Voiced consonant bandwidths widened for smoother transitions.
- Rhotic diphthong collapse: vowel+liquid tied pairs (/ER/ in "shared", "scared", "stairs") now collapse into micro-frame diphthongs with proper formant sweep. Previously rendered as two crushed tokens with no glide.
- SQUARE diphthong pairScale 1.40 for the wide F3 sweep (2500 to 1620 Hz).
- Diphthong rate compensation bumped 0.15 to 0.30; onset hold exponent 1.3 to 1.6 for better vowel identity at high rates.
- Fixed diphthong tie bar blocking dialect replacements: eSpeak marks diphthongs with tie bars (e-tied-I) which blocked I-to-I_es substitution. Vowel-vowel tie bars are now stripped early; affricate tie bars preserved. (issue #82, reported by @gregodejesus2)
- New `I_es` parallel formants tuned to Spanish-peripheral [i] target (Quilis 1981, Martinez Celdran): pf1 330, pf2 2150, pf3 2850. Previously carried English-lax values.
- New `U_es` phoneme for Spanish [u] diphthong offglides (/au/, /eu/): F1=340, F2=780. Base /U/ was English-lax (F1=405, F2=900).
- `autoDiphthongOffglideToSemivowel: false` for Spanish to preserve dialect-specific offglide phonemes.
- Geminate /ss/ deduplication from eSpeak number expansion ("200" no longer "dosssientos").
- Fixed "behind a wall" quality at 22050 Hz: disabled oversampling decimation and anti-alias LP at 22050+ Hz. Sharpness raised 2.0 to 3.0. This was the most-reported audio quality issue since v3.0.
Description
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.
Accessibility
ipadiphonemacrealityDevicetvoswatch
Version history 2 versions
Build 884087365v3.0.12026-04-03 20:39:45
This version adds many new features:
- Higher cascade formants F7 (6500 Hz) and F8 (7500 Hz) for spectral presence above F6 (Rabiner 1968 defaults). Nyquist-proximity fade auto-mutes them at low sample rates.
- Parallel F7/F8 resonators for fricative high-frequency presence (amp 0.15/0.07).
- 2x source oversampling for cleaner harmonics at lower sample rates.
- Dual-oscillator chorus for vocal fold asymmetry (VoicingTone V5): chorus depth and variation sliders for natural vocal fold jitter.
- Brown noise aspiration blend: white/brown noise mix by sample rate (44k=100% white, 22k=70/30, 16k=50/50). Fixes aspiration thinness at lower sample rates.
- Glottal sharpness rebalanced for F7/F8 spectral dynamics.
- Transition bandwidth widening after obstruents: decaying BW boost across first 3 micro-frames, scaled by F2 sweep width.
- Word-final stop audibility improved: stop floor 4ms to 6ms, word-final bonus 5ms to 8ms, voiced alveolar softening eased.
- Voiced consonant bandwidths widened for smoother transitions.
- Rhotic diphthong collapse: vowel+liquid tied pairs (/ER/ in "shared", "scared", "stairs") now collapse into micro-frame diphthongs with proper formant sweep. Previously rendered as two crushed tokens with no glide.
- SQUARE diphthong pairScale 1.40 for the wide F3 sweep (2500 to 1620 Hz).
- Diphthong rate compensation bumped 0.15 to 0.30; onset hold exponent 1.3 to 1.6 for better vowel identity at high rates.
- Fixed diphthong tie bar blocking dialect replacements: eSpeak marks diphthongs with tie bars (e-tied-I) which blocked I-to-I_es substitution. Vowel-vowel tie bars are now stripped early; affricate tie bars preserved. (issue #82, reported by @gregodejesus2)
- New `I_es` parallel formants tuned to Spanish-peripheral [i] target (Quilis 1981, Martinez Celdran): pf1 330, pf2 2150, pf3 2850. Previously carried English-lax values.
- New `U_es` phoneme for Spanish [u] diphthong offglides (/au/, /eu/): F1=340, F2=780. Base /U/ was English-lax (F1=405, F2=900).
- `autoDiphthongOffglideToSemivowel: false` for Spanish to preserve dialect-specific offglide phonemes.
- Geminate /ss/ deduplication from eSpeak number expansion ("200" no longer "dosssientos").
- Fixed "behind a wall" quality at 22050 Hz: disabled oversampling decimation and anti-alias LP at 22050+ Hz. Sharpness raised 2.0 to 3.0. This was the most-reported audio quality issue since v3.0.
Build 882675088v3.02026-03-26 22:59:59
No pricing data captured yet — comparisons appear once the app has paid storefronts or in-app purchases.
Availability 1 of 1 storefronts
| Region | Language | Price | Ratings | Avg | Version |
|---|---|---|---|---|---|
| US | en-US | Free | 0 | — | 3.0.1 |
Change log 5 changes · US
✎
releaseNotes updated
This version adds many new features:
- Higher cascade formants F7 (6500 Hz) and F8 (7500 Hz) for spectral presence above F6 (Rabiner 1968 defaults). Nyquist-pro
✎
description updated
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 wi
✎
name updated
TGSpeechBox
◆
Version 3.0.1 released
This version adds many new features:
- Higher cascade formants F7 (6500 Hz) and F8 (7500 Hz) for spectral presence above F6 (Rabiner 1968 defaults). Nyquist-proximity fade auto-mutes them at low sample rates.
- Parallel F7/F8 resonators for
◆
Version 3.0 released