Directory
Published directory entries matching your search.
MusicGen is a single-stage auto-regressive Transformer model for music generation trained over a 32kHz EnCodec tokenizer with four codebooks, part of the AudioCraft library. It supports text-to-music and text-plus-melody-to-music models ranging from 300M to 3.3B parameters. Running it locally requires a GPU, with at least 16 GB of memory recommended for medium-sized models.
OCRTool.net is a free online OCR tool that extracts text from images, PDFs and screenshots using Mistral AI's OCR model. It supports JPG, PNG, WEBP, BMP, GIF and PDF files up to 20 MB per file, with multi-language recognition and layout-aware conversion. No signup is required, no watermarks are added, and files and extracted text are not stored.
Ondoku is text-to-speech software that reads text up to 5,000 characters free of charge and offers paid plans converting up to 1 million characters a month. Generated audio can be saved as MP3 files and used commercially. It runs in a browser on PC or smartphone without installation.
A Hugging Face Space that generates speech from entered text. Users choose a voice and an emotion style and can optionally set a seed. The app sends requests to the Pollinations service and returns an MP3 file with the synthesized speech.
Sindhi TTS is a Hugging Face Space that generates speech from Sindhi text. Users input text and select a gender for the synthesized voice. The system works best with shorter messages.
Speechify is a text to speech and voice typing assistant that reads books, PDFs, documents and web pages aloud with natural-sounding voices. It offers text highlighting, speed control and scan and listen, and is available as browser extensions, desktop apps for Windows and Mac, and mobile apps for iOS and Android.
Speechma is an online text-to-speech converter that turns text into audio using a library of AI voices. The site states that no registration is required and that generated audio can be used commercially. A REST API for developers is also offered under a monthly subscription.
A free online text-to-speech tool that converts text into speech using an AI voice generator. It offers 100+ voices in 27 languages, allows MP3 download, and lets users adjust speed and pitch. No registration is required.
TTS WebUI is a free Gradio-based web interface for text-to-speech, audio and music generation. It can generate audio from text using over 30 AI models, including Bark, MusicGen, Tortoise and Vocos, and offers voices from the Bark Speaker Directory. Installation is available through one-click installers or manual setup.
VanillaVoice is a free online text to speech tool that reads text aloud with human-sounding voices. Users can pick male, female or child voices in many languages, adjust volume and speed, and download audio as an MP3 without installing software. A Professional Plan offers a commercial license, speech-enabled products and up to 500 words per recording.
XTTS is a Hugging Face Space that provides multi-language text-to-speech functionality. It converts written text into spoken audio across multiple languages, and allows users to optionally upload a short voice recording or use their microphone for voice input.
The Umi-OCR plugin repository contains OCR engines and related components for Umi-OCR, with installation instructions and links to plugin releases.
Acapela Group is a company that develops personalized digital voices using voice AI technology. It offers text-to-speech solutions for services, applications and devices, with support for over 30 languages and more than 200 pre-made voices, plus custom voice creation options. The company provides SDKs for multiple platforms, cloud streaming APIs, and specialized solutions including voice AI for accessibility, transport and customer interaction.
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.
🔥🔥🔥自定义Android相机(仿抖音 TikTok)，其中功能包括视频人脸识别贴纸，美颜，分段录制，视频裁剪，视频帧处理，获取视频关键帧，视频旋转，添加滤镜，添加水印，合成Gif到视频，文字转视频，图片转视频，音视频合成，音频变声处理，SoundTouch，Fmod音频处理。 Android camera(imitation Tik Tok), which includes video editor,audio editor,video face recognition stickers, segment recording,video cropping, video frame processing, get the first video frame, key frame, video rotation, add filter Mirror ,add watermark ,add gif to video, add text to video, picture to video, audio and video synthesis, audio change processing
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.
AssemblyAI provides voice AI infrastructure, including pre-recorded, realtime and synchronous speech-to-text APIs, a voice agent API, speech understanding features and guardrails. Features such as speaker diarization, summarization, sentiment analysis and PII redaction run on the same transcription request.
Boppy is a free AI music generator that creates full songs from a text description. It writes the lyrics and generates a complete track in under a minute, with no signup or credit card required. Tracks run up to 2 minutes, and the apps for iOS and Android add in-app Premium at US$5.99/month in the US.
Text-to-speech solutions with character.
CircleToSearch is an Android app that performs reverse image search by circling content on the screen, with support for multiple search engines including Google Lens, Bing, Yandex, TinEye, ChatGPT and Perplexity. It offers offline OCR text recognition, offline QR detection and works on devices running Android 10 or later without Google Play Services.
Free speech-to-text tool for content creators that accurately transcribes audio & video files up to 2GB.
CRF++ is an open source implementation of Conditional Random Fields for segmenting and labeling sequential data. It is designed for general purposes and can be applied to NLP tasks such as named entity recognition, information extraction and text chunking. Feature sets can be redefined, and it is written in C++ with STL.
Eapy Slide is a tool for creating professional Electronic Press Kits (EPKs) for music artists. Users upload music, images, and text to generate formatted, shareable EPKs to pitch to labels, sync agents, and A&R representatives.
A Hugging Face Space that turns an ebook file or pasted text into a complete audiobook. The user selects a language, voice and audio format, then generates audio to listen to or download; sections can also be previewed and edited. The page states support for 1107+ languages.
