VoiceMake - Text to Speech0.6.0 - App Store

VoiceMake turns text into shareable speech and voiceover audio. Create narration with system voices, Qwen3-TTS, Irodori-TTS, Kokoro TTS, and VOICEVOX character voices such as Zundamon, then preview, adjust, export, and share from your device.

Key Features:

. TEXT TO SPEECH - Paste text and create natural-sounding speech for videos, podcasts, messages, lessons, and creative projects.

. CHARACTER VOICES - Generate expressive Japanese voices with VOICEVOX characters including Zundamon.

. VOICE CLONING - With Qwen3-TTS, record a few seconds of a voice and have it read text in 10 languages, including English, Spanish, and Chinese, in that voice. Irodori-TTS also clones voices for Japanese text and lets you describe the speaking style in Japanese.

. AI VOICE OPTIONS - Use Kokoro TTS for high-quality AI speech, especially when you want natural English voice synthesis.

. ON-DEVICE WORKFLOW - Preview, adjust, and generate audio on your device with bundled or downloaded voice models.

. AUDIO EXPORT - Save generated speech and share voiceover files across your apps.

. VOICE TUNING - Fine-tune pronunciation, intonation, speed, pitch, and other parameters when supported by the selected voice engine.

Perfect for:
- Video narration and short-form content
- Podcast production
- Audiobook and script reading
- Voice messages
- E-learning and presentations
- Accessibility-oriented reading support

VoiceMake combines text-to-speech engines, character voices, and simple editing tools so you can make usable voice audio quickly.

Terms of Use (EULA):
https://www.apple.com/legal/internet-services/itunes/dev/stdeula/

Version History - Added Qwen3-TTS, a new voice engine that speaks 10 languages including English and Japanese. It can also read in a voice you record (voice cloning).
- With Qwen3-TTS, playback starts as soon as the first sentence is ready, so you can start listening to long text right away.
- Irodori-TTS and Qwen3-TTS now even out the pauses between sentences and the volume of each sentence for easier listening.
- Close and Cancel buttons now match the new design. 0.6.0 6h ago - Added Irodori-TTS, a new voice engine. Describe how it should speak in Japanese text, or have it read in a voice you record (voice cloning).
- Rebuilt the Kokoro voice engine.
- Updated for the new design: the player now sits above the tab bar. Tap it to open the full player.
- You can now play audio from above the keyboard while typing.
- Larger screens such as iPad now use layouts that make the most of the space. 0.5.1 1d ago - Added Irodori-TTS, a new voice engine. Describe how it should speak in Japanese text, or have it read in a voice you record (voice cloning).
- Rebuilt the Kokoro voice engine.
- Updated for the new design: the player now sits above the tab bar. Tap it to open the full player.
- You can now play audio from above the keyboard while typing.
- Larger screens such as iPad now use layouts that make the most of the space. 0.5.0 4d ago - Support WebP export. 0.4.10 Jul 29 - Support WebP export. 0.4.9 Jul 28 - Support WebP export. 0.4.8 May 20 - New App Icon
- Bug fixes 0.4.7 Apr 25 - Bugfies 0.4.6 Mar 30 - Bug fixes 0.4.5 Mar 27 - Bug fixes 0.4.4 Mar 25 • Bugfixes 0.4.3 Mar 10 The following speakers have been added:
• Ankomon, Rito, Kurosawa Sae, Yūrei-chan, Nekotsukai Aru, Nekotsukai Bii, Tohoku Kiritan and Tohoku Itako. 0.4.2 Feb 7 • Fixed some bugs 0.4.1 08/29/2025 • Added a new voice type 0.4.0 08/26/2025 • Fixed some bugs 0.3.1 08/20/2025 • Added multilingual voice generation feature. 0.3.0 08/20/2025 • Added a feature to generate voices in bulk 0.2.0 08/18/2025 • Added intonation adjustment feature
• Added output audio format customization feature 0.1.0 08/14/2025 • You can now adjust intonation and other settings when generating speech.
• Improved the UI for a smoother experience. 0.0.2 08/13/2025 0.0.1 08/12/2025