If you want a platform to generate your own audio, Audiobox is a powerful option. It lets you synthesize voices and sound effects from text prompts, with editing abilities like removing background noise or replacing parts of an audio with new sounds. Audiobox is designed for creative and experimental use, so it's a good choice if you want to create new voice styles or transform audio samples based on text prompts.
PlayHT is also worth considering, with a library of more than 600 ultra-realistic AI voices. It also offers custom pronunciations, voice inflections, real-time voice cloning and API integration, so it's good for tasks like video voiceovers, audio publishing and e-learning. PlayHT has an ethics and safety focus, with a free version and several pricing tiers.
If you want a more advanced editing system, check out Descript. Although it's primarily a video and podcast editing tool, it's got advanced multitrack audio editing and AI tools to create clips and generate speech. Descript is good for marketing, sales and learning and development teams, with a free plan and paid plans starting at $12 per person per month.