If you're looking for a tool that can generate voices and sound effects from text prompts and voice input, Audiobox is a good choice. It can generate voices and sound effects based on voice input and natural language text prompts, so it's good for creative and experimental use. The service also lets you generate audio from text prompts, edit audio to remove background noise or replace parts with new sounds, and generate sound effects from text prompts.
Another good option is PlayHT, an AI text-to-speech service that offers more than 600 ultra-realistic AI voices across many languages and accents. It has options for custom pronunciations, real-time voice cloning and API integration, so it's good for a variety of uses like video voiceovers, chatbots and games.
And AI Sound Copilot offers a different approach to generating AI-created sound effects (SFX) for videos and games. You can use it to generate SFX either by uploading a video or with a detailed text prompt, and all the generated sound effects are royalty-free. That makes it a good option for anyone who wants custom sound effects but doesn't want to go through the hassle of licensing.