Generate local text-to-speech audio with Kokoro TTS engine.
npx skills add https://github.com/malue-ai/dazee-small --skill kokoro-tts
Please help me install this Agent Skill. Skill: kokoro-tts Source: https://github.com/malue-ai/dazee-small/tree/main/skills/library/kokoro-tts Command: npx skills add https://github.com/malue-ai/dazee-small --skill kokoro-tts
This Skill provides a high-quality, local, and cost-free text-to-speech (TTS) solution, eliminating the need for API keys and external services.
Use the kokoro-tts skill to convert the text "Hello, this is a test." into an audio file named output.wav using the 'af_heart' voice.
High-intent search queries and answers about installing and using this skill.
Generate speech locally without an internet connection by using the Kokoro TTS engine. It synthesizes high-quality audio directly on your machine, eliminating the need for cloud services or API keys while providing multiple distinct voices.
Convert long articles into audio files without API costs by using offline text-to-speech. The system automatically segments lengthy text into sentences, ensuring continuous audio generation for documents, emails, and articles without per-use charges.
Offline text-to-speech supports multiple voices for different use cases. You can select from distinct voice profiles, such as warm, professional, calm, or energetic, to match the specific tone required for your audio output.
The best way to handle continuous speech synthesis for lengthy text is through sentence segmentation. The engine automatically divides long text into smaller sentences, processing them sequentially to maintain audio quality and flow.
You do not need an API key to synthesize speech on your local machine. The local TTS engine operates entirely offline, removing the need for external service authentication and avoiding any associated per-use charges.
Dependencies required to run kokoro-tts for speech synthesis include kokoro-onnx for the speech engine and soundfile for audio output. These components enable the local generation of high-quality WAV files from text.
Soul-Brews-StudioConvert text to speech using edge-tts neural voices with macOS say fallback.
altrupetsProcess video and audio in Flutter apps with playback, recording, and FFmpeg conversion.
rahulrajaramConvert input text to spoken audio using the Kokoro TTS engine.
MaxSaietsGenerate speech from text offline using sherpa-onnx runtime and voice models.
