Description
Voxelle is an intuitive, browser-based AI voice generator and text-to-speech studio designed to transform written scripts into natural-sounding audio. Powered by Fish Audio S2.1 Pro, the platform provides access to a diverse catalog of 78 licensed voices across 13 languages, enabling users to create expressive speech for a wide range of applications.
Read More
The process is straightforward: users simply write or paste their script into the studio, select a suitable voice from the auditionable catalog, and then generate and download the audio. The tool supports multiple export formats including MP3, WAV, OPUS, and PCM, offering flexibility for different project requirements. Voxelle is entirely web-based, eliminating the need for any software installations, making it accessible from any browser.
Key capabilities include adjustable speaking rates (0.5x to 2x), support for emotion markers, and the ability to handle multi-speaker dialogue with up to four distinct voices in a single script. Each generation request can process up to 1,000 characters. The platform is ideal for creators, educators, and businesses looking to produce high-quality audio content efficiently.
Voxelle operates on a freemium model. Upon signing in with Google and performing a daily check-in, users receive a free allowance of 1,500 characters per day for personal, non-commercial evaluation. This allowance resets daily at 00:00 UTC and does not roll over. For commercial use and higher character volumes, paid plans are available starting from $5 per month, which include a commercial license for the generated audio. It's important to note that voice identity rights are not transferred with the commercial license.
The service is built on Fish Audio's S2.1 Pro technology, which is described as turning text into "lifelike speech." Voxelle acts as the interface, providing the studio environment, voice previews, generation controls, and audio downloads, while adhering to its own pricing and usage terms. The platform is regularly maintained and updated, ensuring a reliable experience for its users.
- CategoryAI Voice Generators
- Pricing ModelFreemium
- DeploymentCloud
- PlatformsWeb
Voxelle's Core Features
Browser-based AI voice generator
Text-to-speech conversion
78 licensed voices available
Supports 13 languages
Multiple audio export formats (MP3, WAV, OPUS, PCM)
Adjustable speaking rate (0.5x – 2x)
Emotion markers for expressive speech
Multi-speaker dialogue (up to 4 speakers)
1,000 characters per generation request
Free daily character allowance with sign-in
Commercial license available with paid plans
No software installation required
Auditionable voice catalog with public samples
Powered by Fish Audio S2.1 Pro
How to use Voxelle?
Write or Paste Script: Input your text, ensuring it fits within your character allowance.
Pick a Licensed Voice: Browse the catalog, listen to public samples, and select a voice that matches your needs.
Generate Audio: Initiate the text-to-speech conversion within the browser studio.
Download Audio: Export your generated speech in MP3, WAV, OPUS, or PCM format.
Voxelle's Use Cases
- Narration and Podcasts
- Lessons and Explainers
- Short Video Localization
- Audiobook Creation
- Marketing Content
- Accessibility Features








