Clone custom voices from audio samples and synthesize speech via iFlytek APIs.
npx skills add https://github.com/iflytek/iFly-Skills --skill ifly-voiceclone-tts
Please help me install this Agent Skill. Skill: ifly-voiceclone-tts Source: https://github.com/iflytek/iFly-Skills/tree/main/ifly-voiceclone-tts Command: npx skills add https://github.com/iflytek/iFly-Skills --skill ifly-voiceclone-tts
Clone a custom voice from audio samples and synthesize speech with the cloned model, enabling personalized voice experiences without relying on generic TTS voices.
Run the training workflow to create a task, upload audio, submit training, and obtain a res_id, then use it to synthesize speech with your cloned voice.
High-intent search queries and answers about installing and using this skill.
Voice cloning for TTS involves training a model on user audio samples to generate a res_id, then synthesizing speech with the cloned model. It enables personalized voices for IVR, audiobooks, and multimedia.
You need a stable Python environment using pure-stdlib tooling and environment variables IFLY_APP_ID, IFLY_API_KEY, and IFLY_API_SECRET configured to access iFlytek Voice Clone APIs for training and synthesis.
No pip dependencies are required. The implementation is self-contained using pure Python stdlib-based tooling, meaning you can run the training and speech synthesis workflow within a standard Python environment.
Use cloned voice TTS when creating branded IVR prompts, narration for videos, or accessibility features requiring a personalized voice, rather than relying on generic TTS voices for your multimedia applications.
Run the training workflow to create a task, upload your audio samples, and submit training to obtain a res_id, then synthesize speech by providing text alongside the res_id to generate audio with your cloned voice.
Yes, you can clone your custom voice from audio samples and synthesize speech with the cloned model to create branded IVR prompts, audiobook narration, and multimedia content using pure Python stdlib tooling.
JaykaijackClone a speaker's voice from example audio and synthesize speech via iFlytek WebSocket.
desirecoreConvert input text into speech audio using MiniMax's T2A API.
bitan-delTranscribe audio files to text or JSON via OpenAI's Whisper API.
heyzudeGenerate speech audio from text using the OpenAI Audio API.
