AI Voice

I. AI Voice

Rendora provides high-naturalness Text-to-Speech (TTS) functionality. Simply input text to generate character voices in various styles. The built-in voice library offers abundant voice assets, allowing you to freely select, preview, and favorite preferred voices on this interface.

II. Using Voice

Voice Library

Rendora's voice library contains a wealth of AI voices, filterable by gender, age, style, language, and other dimensions.

• Gender: Male, Female
• Style: Clam, Gentle, Deep, Sweet, Cheerful, Passionate, Professional, etc.
• Language: Chinese, Chinese dialects, English, Arabic, Dutch, Filipino, French, German, Indonesian, Italian, Japanese, Khmer, Korean, Lao, Malay, Portuguese, Russian, Spanish, Tamil, Thai, Vietnamese, etc.
• Scenario: Content Creator, Customer Experience, IT & Cybersecurity, Lifesharing, Learning & Development, Enterprise Marketing, Business Operation, Event Promotion, Sales Enablement, Social Media, Lifesharing, Job & Career, E-commerce, Education, News Media, etc.
• Type: Basic, Pro.

On the Rendora platform, you can access the voice library from multiple entrances to view voice effects or use voices.

Operation Paths

You can access the Rendora voice library from multiple locations to view voice effects or use voices.

• Entrance 1: In the workbench, click the [Voices] module on the left to view the voice library (Voice Library in Workbench)
• Entrance 2: During creation, find the [Voices] module in the top navigation bar of the editor to view the voice library (Voice Library in Editor)

Voice Versions

AI voices in Rendora's voice library are divided into Basic version and Pro version. Both achieve high similarity restoration through specialized technology, delivering natural and realistic sound effects.

Version Classification

1. Basic: Generated based on online small-model TTS, with fluent and clear speech to meet daily usage needs.
2. Pro: Powered by the latest large-model technology, significantly enhancing speech naturalness and expressiveness. It can generate movie-level human voices with rich emotional changes, suitable for high-standard scenarios such as high-quality video dubbing and content promotion.

Coin Consumption Standards

Different voice versions have different coin consumption standards, as follows:

1. Using the Basic version voice throughout video production does not consume coins.

2. Previewing Pro version voices on the voice selection page or text box does not consume coins.

3. Selecting the Pro version voice for 3D generation is charged by video duration, consuming 5 coins per minute.

4. Selecting the Pro version voice for video export is charged by video duration, consuming 5 coins per minute.

Voice Cloning

For details about voice cloning, enter the [Lab] to view specific operations.

⚠️ Tip: Currently, voice cloning only supports cloning English voices.

III. FAQ

1. Can cloned voices be used for video production?

Yes. Cloned voices are automatically added to your personal voice library for free use within the Youyan platform.

2. Why is previewing the Pro voice free while 3D generation is charged?

Both 3D generation and preview are powered by large models. To provide users with a better experience and trial opportunity, all computing power consumption is waived during preview, and coins are only charged after the actual result is generated.

3. If I cancel the operation midway while making a video with the Pro version voice, will the coins for the Pro version voice be deducted?

No coins for the Pro version voice will be deducted if you do not click the Generate/Export button. Once generation is completed, even if not exported, charges will be based on the actual duration.

4. How to check the consumption record of the Pro version voice?

Go to "Account Center - Consumption Details" to view. Consumption of "Pro Voice" is merged into the details of 3D generation/exported finished videos.