Voocaly Documentation
Learn how to use the AI Voice Studio workstation, apply emotion tags, configure playback speed, and export studio-quality audio.
1. Studio Workstation Guide
The Voocaly Studio interface allows you to draft scripts, select from 115 neural voices across 10 global locales, fine-tune playback speed (0.5x to 2.0x), and export generated audio to MP3 or lossless WAV formats.
Supported Emotion Tags
Insert emotional cues directly into your script to guide speech synthesis cadence and tone:
2. Plan Allowances & Script Limits
Each account tier includes dedicated monthly credit allowances and maximum characters permitted per single script generation:
| Plan | Monthly Credits | Max Chars / Script | Cloning Quota | Commercial Rights |
|---|---|---|---|---|
| Free | 18,000 | 2,000 chars | 1 public clone | Personal only |
| Starter | 100,000 | 3,500 chars | 5 public clones | Commercial |
| Creator | 220,000 | 5,000 chars | 7 private/public | Commercial |
| Scale | 550,000 | 5,000 chars | 10 private/public | Commercial |
3. Custom Voice Cloning Guide
Voocaly allows you to generate personalized AI voices by providing clean reference audio:
- Audio Quality: Upload 10 to 30 seconds of clean, single-speaker speech without background music, echo, or overlapping voices.
- Privacy Modes: Free and Starter tiers generate public catalog voices; Creator and Scale plans support private voice clones exclusive to your account.
- Voice Rights: You must hold the legal rights or consent of the speaker for any voice sample you clone.
4. Developer API Availability
Voocaly operates exclusively as a web-based studio application. A public third-party REST API, developer API key issuance, and developer SDK are not currently offered.
All voice synthesis, audio rendering, and account management are conducted directly through the browser application at voocaly.com/studio.