Generate speech from text with adjustable speed
Whisper model to transcript japanese audio to katakana.
IndicParler_TTS for Urdu_Punjabi & Sindhi
Generate text transcripts with timestamps from audio or video
StyleTTS2 trained on ukrainian dataset
Generate high-quality speech from text with specified emotion and voice
Turn Any Article to Podcast
Generate anime character speech from text
Cloning Voice tokoh Indonesia - Bahasa Indonesia
Generate speech using a speaker's voice
Transcribe audio from microphone, file, or YouTube link
Transcribe or translate audio and YouTube videos
F5-TTS & E2-TTS: Zero-Shot Voice Cloning (Unofficial Demo)
WebAssembly English Text-to-Speech (TTS) using sherpa-onnx is a powerful tool that converts text into natural-sounding speech. It leverages the WebAssembly (WASM) platform for high-performance execution and is optimized for cross-platform compatibility. sherpa-onnx is designed to generate high-quality English speech synthesis with adjustable speed settings, making it suitable for a wide range of applications, from web-based interfaces to standalone desktop tools.
• Adjustable Speed: Users can control the speed of the generated speech to suit their preferences.
• High Performance: Built with WebAssembly, ensuring fast and efficient speech synthesis.
• Cross-Platform Compatibility: Runs on multiple platforms, including web browsers, desktop, and mobile environments.
• Lightweight: Optimized for low-resource consumption, making it ideal for real-time applications.
npm install @mailchimp/sherpa-onnx
import { Speaker } from '@mailchimp/sherpa-onnx';
const speaker = new Speaker();
speak() method.
speaker.speak('Hello, world!');
speechRate property.
speaker.speechRate = 1.5; // Speeds up the speech by 50%
What platforms does WebAssembly English TTS support?
WebAssembly English TTS (sherpa-onnx) supports all major platforms, including Windows, macOS, Linux, and web browsers that support WebAssembly.
Can I adjust the speed of the generated speech?
Yes, you can adjust the speech rate using the speechRate property. For example, setting it to 1.5 will speed up the speech by 50%.
Is the sherpa-onnx library suitable for real-time applications?
Yes, sherpa-onnx is optimized for low latency and high performance, making it ideal for real-time applications such as voice assistants or interactive web interfaces.
How do I integrate sherpa-onnx into my web application?
You can integrate sherpa-onnx by importing the library and initializing the speaker as shown in the usage section. Ensure you have the necessary dependencies installed.
What are the system requirements for using sherpa-onnx?
sherpa-onnx requires a system that supports WebAssembly. Most modern browsers and operating systems meet this requirement.
Can I use sherpa-onnx for commercial purposes?
Yes, sherpa-onnx is available under a permissive license, allowing for both personal and commercial use.