iZotope VocalSynth
VocalSynth 2 is an immersive vocal experience that evolves with your productions. Get vocoder, compuvox, polyvox, talkbox, and the all-new biovox with seven stomp-box style effects, all from one powerful plug-in. Color and shape vocals with five blendable creative must-haves and stompbox-style studio effects. A one-stop for past, present, and future vocal sounds. Get lost in layers, textures, effects, blending, and morphing in an experimental effects playground designed to help you craft your own signature vocal sound. Perfect your vocal tone with the drag-and-drop, 7-module multi-effects chain. An advanced spectral display reacts to the sonic characteristic of vowels and blends fun interaction with a unique metering experience. VocalSynth 2 works within the iZotope ecosystem to connect with other plugins like Neutron, Ozone, and Tonal Balance Control. Auto, MIDI, and sidechain modes allow control over vocoder-inspired effects and unique signal modulation for added creativity.
Learn more
Voice Changer Pro X
Voice Changer Pro X is “the ultimate live voice transformer” and comes with the sound engine and over a hundred tweakable presets of our professional #1 music app voice synth. Speak, sing, hum and beatbox in the mic, to turn your voice live into a baby or tenor, a popstar on autopitch, a Hollywood-class robot, a church or close harmony choir, animals from birds to dogs and lions, musical instruments from organs, guitars and a groovy bass to percussions and rich 70's vocoders, amazing effects and ambient, lush string/storm soundscapes. Voice Changer Pro X includes a massive and fully tweakable robot voice preset for free. Get 100+ original Voice Synth presets via one single in-app purchase.
Learn more
Seed-Music
Seed-Music is a unified framework for high-quality and controlled music generation and editing, capable of producing vocal and instrumental works from multimodal inputs such as lyrics, style descriptions, sheet music, audio references, or voice prompts, and of supporting post-production editing of existing tracks by allowing direct modification of melodies, timbres, lyrics, or instruments. It combines autoregressive language modeling with diffusion approaches and a three-stage pipeline comprising representation learning (which encodes raw audio into intermediate representations, including audio tokens, symbolic music tokens, and vocoder latents), generation (which transforms these multimodal inputs into music representations), and rendering (which converts those representations into high-fidelity audio). The system supports lead-sheet to song conversion, singing synthesis, voice conversion, audio continuation, style transfer, and fine-grained control over music structure.
Learn more
Vocode
Vocode is an open source library that simplifies the creation of voice-based applications leveraging large language models. Developers can build real-time streaming conversations with LLMs and deploy them to phone calls, Zoom meetings, and more. Vocode provides easy abstractions and integrations so that everything you need is in a single library. It offers out-of-the-box integrations with leading speech-to-text and text-to-speech providers, including AssemblyAI, Deepgram, Google Cloud, Microsoft Azure, and Whisper. The platform supports cross-platform deployment across telephony, web, and Zoom, enabling applications like LLM-powered phone calls, personal assistants, and voice-based games. Vocode's modular design allows for seamless integration of various AI models and services, providing developers with the flexibility to choose the best components for their applications. The platform also supports multilingual capabilities.
Learn more
