Voice Generator:

Transform your projects with lifelike speech synthesis! With Voice Generator, seamlessly integrate cutting-edge MeloTTS technology into Blender's Video Editing workspace. Synthesize natural-sounding speech from text in various languages and accents. Elevate your animations, tutorials, and presentations with ease. Whether you're working on animation projects, video editing, or multimedia presentations, this add-on provides a convenient way to add natural-sounding voiceovers to your creations.

As of right now the voice generator has all female voices for the following languages: English (US), English (UK), English (India), English (Australia), Spanish, French, Chinese, Japanese, and Korean. Using the add-on requires internet connection.

Voice Generator 2.0: 

With Voice Generator 2.0, you have access to a wide range of speaker options, including various accents and languages. Need to switch between languages or include code-switched text? Voice Generator 2.0 handles it effortlessly, even adapting the accent to match the language for an immersive experience.

The addon supports speech synthesis in multiple languages, including English, German, Spanish, French, Japanese, Italian, Hindi, Korean, Polish, Portuguese, Russian, Turkish, and Chinese.

Moreover, it goes beyond speech, offering nuanced non-speech sounds and music generation capabilities. From laughter and sighs to music lyrics and speaker prompts, you can add depth and realism to your audio tracks. Whether you're creating dialogue-heavy scenes or musical compositions, Voice Generator 2.0 provides the tools you need to achieve professional results. Elevate your video editing workflow with Voice Generator 2.0 and unleash your creativity like never before.

This addon uses the Bark universal text-to-audio model created by [Suno](www.suno.ai) and the huggingface space they provide. In order for the addon to work you have to have internet connection.

You can check out my other very useful Blender add-ons: