AI Voice Studio

Create natural, expressive narration in seconds.

⚡ Quick Presets
Narration Script
Chars: 0 Words: 0 Est. Duration: 00:00
⚡ ~145 WPM Speech Pace 📦 1 Audio Segment 📝 0 Sentences
Voice Profile
Narration Style
Storytelling
Emotion Preset
Neutral
Voice Dynamics & Language
Advanced Voice Direction Custom AI Prompt

Write custom directorial instructions. This is merged with your category, emotion, and parameter settings.

Generating your voice... 0%
Voice: Orion (Cinematic) Style: Storytelling Est: 00:00
Generated Voice Narration WAV 24kHz
Voice: Orion Style: Cinematic Language: English 327 words / 1,842 chars
00:00
00:00

Voice Library

Explore studio-tuned voice profiles mapped to Google Gemini TTS prebuilt voices.

Narration History

Recent voice generations stored locally on your device.

Google Gemini API Configuration
Enter your Google Gemini API key to synthesize natural audio via Gemini TTS models.
Gemini API Key
Obtain a free or paid API key at aistudio.google.com
TTS Model
Current officially supported Gemini Flash TTS model
Remember on this device
If unchecked, your API key stays only in browser session memory and is cleared upon tab close.
Frontend Security Notice: Frontend-only API keys can be exposed to anyone who can inspect the application. For personal/local use this is acceptable, but do not use this architecture for a public production service.
Studio Defaults
Customize default preferences when opening VOXERA.
Default Gender
Default Language
Local Data & Privacy
Manage locally stored caches and generated project histories.
Reset Local Storage
Clears API key, saved voice project history, and user settings.
System Information
Application: VOXERA AI Voice Studio v2.4
Runtime: Pure Vanilla HTML5 / CSS3 / ES6+ JavaScript (Zero external UI frameworks)
API Provider: Google Gemini API v1beta (generateContent)
Supported TTS Model: gemini-3.1-flash-tts-preview
Official Prebuilt Voices: Puck, Charon, Kore, Fenrir, Zephyr
Audio Pipeline: Native Linear PCM (24,000 Hz, 16-bit Mono) converted to RIFF WAV container