Directory
Published directory entries matching your search.
Audio diffusion library for PyTorch that includes models for unconditional audio generation, text-conditional audio generation, diffusion autoencoding, upsampling, and vocoding. The models are waveform-based, and the U-Net, DiffusionModel, diffusion method, and samplers are customizable for other formats. No pre-trained models are provided.
AudioCraft is a code base for generative audio tasks including music, sound effects, and compression, trained on raw audio signals. MusicGen produces music samples from text inputs, and AudioGen produces audio from environmental sounds via text-to-sound generation. The models use the EnCodec neural audio codec to learn discrete audio tokens from waveforms.
Zenmic.com is an AI audio generation tool that converts text, documents, URLs or topics into natural-sounding audio. It is targeted at ESL teachers, learning and development teams, and podcast creators, and offers features including full script control, over 30 voices, MP3 export, support for 125 languages, up to six speaker tracks, and voice cloning. Users can start using the tool for free without a credit card.
AudioLDM is a text-to-audio system built on a latent space that learns continuous audio representations from CLAP latents. It generates text-conditional sound effects, human speech and music, and enables zero-shot text-guided audio style transfer, inpainting and super-resolution.
This Automatic Speech Recognition Hugging Face Space converts spoken audio to written text. Users can upload audio files, record from their microphone, or provide an audio URL, and select options including language, model, decoding method, and punctuation.
AIVocal is an AI-powered voice assistant platform. It provides tools for AI voice generation, voice cloning, text-to-speech, speech-to-text, vocal removal, audiobook generation, podcast generation and audio transcription, serving creators and professionals for voice-related work.
StemGen is an end-to-end music generation model trained to listen to musical context and respond appropriately. It is built on a non-autoregressive language-model type architecture similar to SoundStorm and VampNet, and is presented as examples for an ICASSP2024 paper.
Harmonai is a Stability AI lab that releases open-source generative audio tools for music production. Its stated goal is to make music creation more accessible and enjoyable for all users, with tools that support custom infinite sound library generation to expand creative possibilities for musicians.
Lyria by Google DeepMind is a music generation model developed by Google DeepMind, positioned as the organization's most advanced system for AI-powered music creation. It is designed to support creative music production alongside related AI experiments, as part of Google DeepMind's broader portfolio of specialized AI models for generating high-fidelity music and audio.
This Automatic Speech Recognition Hugging Face Space processes audio files, microphone recordings, or audio clips up to 40 seconds from a URL, and outputs the spoken content as written text.
MusicGen is a Hugging Face Space by facebook that generates music audio from a text description. Users can optionally upload a short melody to guide it and set parameters such as length; the app then creates a music audio file.
This Hugging Face Space by Xenova is a web application that converts user-entered text to spoken audio. Users can type or paste text into the app, which generates clear audio playback of the content without requiring file uploads.
This Hugging Face Space by k2-fsa is a text-to-speech application that converts user-entered text to spoken audio. Users can select a language or model, and may upload or record a short reference audio clip to generate speech in a specific person's voice.
Tunisian Speech Recognition is a Hugging Face Space created by SalahZa. The application transcribes spoken Tunisian Arabic into text using Arabic characters. Users can provide input audio either by recording through a microphone or uploading an audio file, and the tool returns the corresponding text transcription.
voicetoinstrument.com is an AI audio conversion platform that transforms uploaded voice recordings, hummed melodies, or vocal tracks into realistic instrument sounds. It supports conversion to more than 100 instruments including piano, guitar, violin, saxophone, drums, and flute, and offers a free online converter alongside additional AI audio tools such as stem splitters and vocal removers.
A YouTube Blog post announcing an early look at the company's first AI-related music experiments: Dream Track for Shorts and Music AI tools, built in collaboration with Google DeepMind. Dream Track is powered by the Lyria music generation model and initially lets a small group of select US creators create soundtracks of up to 30 seconds for Shorts.
FAL.ai (Seedance 2.0) is ByteDance's Seedance 2.0 video generation API hosted on the fal serverless platform, launched April 9, 2026. It produces cinematic video with native audio, real-world physics, and director-level camera control, accepting text, image, audio, and video inputs. The service offers fast and standard API tiers for text-to-video, image-to-video, and reference-to-video generation, supporting 480p and 720p output.
Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch.
MubertAI/Mubert-Text-to-Music is a GitHub repository maintained by MubertAI. It hosts a simple notebook that demonstrates prompt-based music generation via the Mubert API, providing a reference implementation for users looking to generate music from text prompts using the service.
MuseGen is an AI music generation studio that turns text prompts into songs. It composes melodies, lyrics and vocals, offers multi-genre styles, and allows editing and export in MP3, WAV or MIDI. It also separates tracks into stems and can turn songs into MIDI or music videos. A paid subscription gives monthly credits for generating videos, images and songs.
Qwen3-TTS is an open-source series of text-to-speech models developed by the Qwen team at Alibaba Cloud. It supports speech generation, streaming output, free-form voice design and voice cloning, and covers ten major languages with dialectal voice profiles. The release includes models of 0.6B and 1.7B parameters.
Fish Audio is an AI platform for voice generation, voice cloning, and audio storytelling, and its GitHub organization hosts open source repositories. Public repositories include fish-speech, described as SOTA open source TTS, Bert-VITS2, a vits2 backbone with multilingual-bert, and fish-diffusion, a TTS / SVS / SVC framework.
AI Mastering is an automated online audio mastering service that uses AI. Free mastering is available, with drag-and-drop uploading, target loudness and mastering level customization, and output format, spectrum and loudness analysis. An API is documented, and a desktop offline version has been released.
A web tool for generating songs from text, lyrics or uploaded audio, with style, voice and tempo options and instrumental-only tracks. Songs can be downloaded or shared. The free tier offers 20 daily credits and royalty-free output.
