Aureola's Automated Voices is a development tool for converting JSON, CSV, or TXT files into audio using AI text-to-speech services like PlayHT and ChatGPT. It's suitable for creating voice-overs or game audio, offering a range of voices and customization options. PlayHT supports the creation of custom voice clones. The integrated TTS services include free options for non-commercial use, support multiple languages and audio formats (MP3, WAV), though English is universally supported across all providers.

• 1-Click Conversion: Converts JSON, CSV, or TXT files into audio files using AI text-to-speech services like PlayHT and ChatGPT.

• Wide Range of Voices: Offers a variety of voices for creating voice-overs or game audio, enhancing the auditory experience of projects.

• Custom Voice Creation: With PlayHT, users can create custom voice clones, offering unique customization options for project needs.

• Free and Paid Options: Integrated text-to-speech services include free options for non-commercial use, making it accessible for projects of all scales.

• Supports Various Audio Formats: Users can export their audio in popular formats like MP3 and WAV, ensuring compatibility with a wide range of platforms.

• Customization Wizard: For complex requirements, a wizard is available to fine-tune all settings, from voice type to style options.

ChatGPT

ChatGPT's Text to Speech (TTS) capabilities enable the conversion of text into natural-sounding audio in multiple languages and dialects, leveraging advanced speech synthesis technology. Through its API, ChatGPT allows for easy integration into various applications, supporting the automated generation of voiceovers, audiobooks, and other spoken word content.

Features

• Currently offers 6 different voices.

• Supports multiple languages and dialects.

• Voice generation is fast and reliable.

Pricing

OpenAI offers several different pricing tiers for Audio models:

• TTS: $15.00 / 1M characters

• TTS HD: $30.00 / 1M characters

For detailed information, please visit OpenAI's pricing page. Please note that our Usage Policies require you to provide a clear disclosure to end users that the TTS voice they are hearing is AI-generated and not a human voice.

PlayHT

Play.ht is a cutting-edge Text to Speech (TTS) platform that transforms text into lifelike audio content in various languages and accents. Its API enables seamless integration for automating audio content creation, featuring an extensive range of realistic voices. Notably, Play.ht also offers the capability to create custom voice clones, enhancing personalization and brand consistency across audio content.

Features

• Offers a variety of voices for creating voice-overs or game audio.

• Offers a wide range of customization options for voice type, style, and more.

• Can be used to create custom voice clones, offering unique customization options for project needs.

• Can be used for free in non-commercial projects.

• PlayHT claims to be the fastest TTS service on the market.

Pricing

PlayHT offers several different plans for Audio generation including a free plan:

• Free Plan: $0.00 / 12,500 characters per month, 1 Instant Voice clone, non-commercial use only!

• Hacker: $5.00 / 25,000 characters per month, $0.25 per every additional 1000 characters, 10 Instant Voice clones.

• Startup: $299.00 / Up to 1.5 million characters (~ 33 hours) per month, $0.20 per every additional 1000 characters, 750 instant clones.

• Growth: $999.00 / Up to 10 million characters (~ 225 hours) per month, $0.10 per every additional 1000 characters, Unlimited instant clones.

For detailed & up to date information, please visit PlayHT's pricing page.

This package should work in all currently supported Unity versions. If you have any questions or need help with the package, join the Discord Server.