# TTS

kokoro-onnx is a text-to-speech (TTS) project based on the Kokoro model and ONNX runtime. It supports English and plans to support French, Japanese, Korean, and Chinese. The model offers near real-time performance on macOS M1 and provides a variety of voice options, including whispering. The model is lightweight, approximately 300MB (around 80MB when quantized). This project is open-source on GitHub under the MIT license, facilitating easy integration and use for developers.

Flash is ElevenLabs' latest text-to-speech (TTS) model, generating speech at a speed of 75 milliseconds plus application and network latency, making it the preferred choice for low-latency, conversational voice agents. Flash v2 supports only English, while Flash v2.5 supports 32 languages, consuming 1 credit point for every two characters. In blind tests, Flash consistently outperformed other low-latency models, proving to be the fastest with guaranteed quality.

Auralis is a text-to-speech (TTS) engine that converts text into natural speech quickly, supports voice cloning, and boasts extremely fast processing speeds—capable of handling an entire novel in just minutes. The product is distinguished by its high speed, efficiency, easy integration, and high-quality audio output, making it suitable for scenarios requiring rapid text-to-speech conversion. Built on a Python API, Auralis supports long text streaming, built-in audio enhancement, automated language detection, and more. Developed by AstraMind AI, Auralis aims to provide a practical TTS solution for real-world applications. While product pricing is not explicitly stated on the page, the codebase is released under the Apache 2.0 License, allowing for free use in projects.

ClipTurbo (小视频宝) is an AI-driven video generation tool designed to help users easily create high-quality marketing videos. It utilizes AI technology for copywriting, translation, icon matching, and TTS voice synthesis, ultimately rendering videos using manim to avoid the throttling issues faced by purely generative AIs on platforms. ClipTurbo supports multiple templates, allowing users to choose resolution, frame rate, aspect ratio, or screen orientation, with templates automatically adapting. It also supports various voice services, including the built-in EdgeTTS. Currently, ClipTurbo is still in the early development phase and is only available to registered users of Sanhua AI.

Ortlin is a web-based graphical user interface designed to help anyone, tech-savvy or not, easily interact with OpenAI's API and underlying models. It is completely free and open-source, allowing users to utilize the powerful capabilities of OpenAI without any barriers.

Voice-Pro is an integrated solution for subtitles, translation, and text-to-speech (TTS). It supports adding multilingual subtitles and audio to videos, enabling content creators to expand their reach to global markets. The product utilizes OpenAI Whisper and open-source translation and TTS technologies for easy installation and portability. It is also equipped with a Vocal Remover, leveraging the UVR5 and Meta's Demucs engine to enhance speech recognition accuracy.

Parler-TTS is a lightweight text-to-speech (TTS) model developed by Hugging Face that can generate high-quality, natural-sounding speech in a given speaker style (gender, tone, speaking style, etc.). It is an open-source implementation of the paper "Natural language guidance of high-fidelity text-to-speech with synthetic annotations" by Dan Lyth and Simon King from Stability AI and the University of Edinburgh, respectively. Unlike other TTS models, Parler-TTS is fully open-source, including the dataset, preprocessing, training code, and weights. Features include: * Generation of high-quality, natural-sounding speech output * Flexible usage and deployment * Provision of a rich annotated speech dataset. Pricing: Free.

VoiceBar provides the most realistic AI voice synthesis service, including multi-language and accent options. It features advanced voice quality and a sense of realism. It offers competitive pricing and does not require a subscription. Suitable for voice messages, multi-language text-to-speech, TikTok, voiceover videos, and learning.

Unreal Speech is a text-to-speech API that converts text to speech, helping users significantly reduce voice synthesis costs. It is 20 times cheaper than Eleven Labs and Play.ht, and 4 times cheaper than Amazon, Microsoft, and Google. Unreal Speech provides high-quality voice synthesis and offers personalized voice and format options to meet user needs. The API also supports real-time demos and comparisons with other speech synthesis engines. Pricing is based on character count and audio duration, with discounts offered for increased usage.

Voice Remaker is a completely free, embedded AI voice generation tool that uses cutting-edge synthesis technology to create audio that's as close to natural speech as possible. It supports AI text-to-speech, history tracking, audio file download, and deletion features. With Voice Remaker, you can instantly convert text into natural-sounding voices and save them as MP3 files.