Synthesize speech from text using preset or cloned voices via ominix-api.
npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-fm
Please help me install this Agent Skill. Skill: mofa-fm Source: https://github.com/mofa-org/mofa-skills/tree/main/mofa-fm Command: npx skills add https://github.com/mofa-org/mofa-skills --skill mofa-fm
MoFA FM provides high-quality text-to-speech with preset voices and optional custom voice cloning via ominix-api, enabling scalable audio production without manual recording.
Call fm_tts with the full text to generate speech and receive the audio file.
High-intent search queries and answers about installing and using this skill.
To convert text to speech on macOS, you can use custom voice cloning by uploading a reference audio clip to create a named voice, then synthesize speech from text using that cloned voice via the ominix-api.
Yes, local voice management allows you to save, list, and delete custom cloned voices. You can set a default voice to streamline future text-to-speech generation tasks.
Text-to-speech generation supports WAV and MP3 output formats. Generated audio files are delivered locally to your macOS environment for immediate playback or integration.
You can shape voice-over output by applying language settings, emotion prompts, and speed control parameters during speech synthesis to match different contextual requirements.
Yes, preset voices like Vivian, Serena, and Ryan enable quick text-to-speech for accessibility read-alouds, providing scalable audio production without manual recording.
Yes, voice cloning and TTS synthesis require a macOS environment to function, as local voice management and audio file delivery are enforced through macOS system operations.
cnbisonTranscribes audio files to text and synthesizes expressive speech in multiple languages.
levanminhducConvert, encode, extract, and stream audio and video with FFmpeg.
team-telnyxConvert text into speech audio using the Telnyx Text-to-Speech API.
skills-routerGenerate speech with voice cloning and transcribe audio to TXT, SRT, or ASS formats.
