AI Voice & Audio

Google Illuminate turns research papers into AI-generated audio summaries to help users understand their content.

Audacity AI Plugins adds effects such as noise reduction and music separation to Audacity editing.

The voice-changer project provides real-time voice changing for audio.

OpenVINO AI plugins add effects, generators, and analyzers to Audacity, running locally on a PC.

Altered Studio changes voices using curated or custom AI voices, with tools for real-time voice effects, accent translation, and voice restoration.

ELSA Speak teaches English pronunciation and speaking through practice exercises and personalized feedback.

insanely-fast-whisper accelerates Whisper transcription using Transformers, Optimum, and flash attention.

KreadoAI generates video ads, images, and copy from product inputs, with AI avatars, multilingual output, and platform exports.

The whisper.cpp project ports OpenAI’s Whisper speech recognition model to C and C++.

Podwise turns podcast episodes into summaries, transcripts, mind maps, and insights that listeners can revisit.

Sesame’s article discusses conversational voice and the qualities that make spoken interactions feel present.

Addsubtitle translates video subtitles and voice into more than 100 languages through a browser-based tool.

AI Wedding Toast generates personalized speeches for roles such as best man, maid of honor, and father of the bride.

Vocalist.ai provides AI tools for music production, including vocal transformation, pitch correction and stem splitting, with royalty-free commercial use.

Speechlab localizes audio and video with dubbing, captions, and subtitles in more than 50 languages.

Gotalk.ai generates voiceovers from text with more than 120 voices across 50 languages.

Deepfake Detector analyzes videos and audio for signs of AI manipulation, with a page describing use by media and research teams.

Vosk provides an offline speech recognition API for mobile devices and servers, with several programming language interfaces.

EmotiVoice provides a multi-voice text-to-speech engine with prompt controls.

ESPnet includes tools for end to end speech processing and related speech tasks.

Microsoft Clipchamp is an online video editor for recording, editing, and sharing videos, with templates and stock media.

Podsqueeze creates podcast transcripts, summaries, show notes, newsletters, clips, social posts, and audio enhancements.

Text-to-Audio Generation with Latent Diffusion Models - Speech Research.

LANDR combines AI mastering with music distribution, plugins, samples, collaboration tools, and courses.