Authenticated User Features
The features below are available once you sign in. Each item explains what happens behind the scenes and the benefit you get as a creator.
-
Daily generation quota (3 per day)
- How it works: The server tracks your daily count and unlocks the next batch every 24 hours.
- Benefit: Fair access for everyone and predictable performance during peak usage.
-
Text input with guardrails
- How it works: You can enter up to 1,000 characters; the server enforces the limit for consistency.
- Benefit: Faster generation times and clean, reliable output length.
-
Voice library (4 voices)
- How it works: Choose from a curated set of voices; the server validates the selection before rendering.
- Benefit: Match narration style to your brand or audience quickly.
-
Tone presets (6 tones)
- How it works: Select a tone, and the system adds a friendly prompt to steer the delivery.
- Benefit: Consistent emotional delivery without manual tuning.
-
One-click generation
- How it works: The app sends your text, voice, and tone to the server, which calls Gemini to synthesize audio.
- Benefit: High-quality speech in seconds without studio tooling.
-
Playback timeline
- How it works: You can play/pause and scrub the timeline to review specific moments.
- Benefit: Faster editing decisions and quick QA before download.
-
Speed, volume, and mute controls
- How it works: Adjust playback speed (0.5x to 2x) and volume in the player without re-rendering.
- Benefit: Review pacing and clarity instantly, saving regeneration time.
-
Live visualizer modes
- How it works: Switch between bars, waveform, or orb styles, plus color and speed controls.
- Benefit: Visual feedback while listening, helpful for reviews and demos.
-
Download-ready audio files
- How it works: Download your result as MP3 when available, with WAV as a fallback.
- Benefit: Quick publishing to podcasts, videos, LMS, or product tours.