Convert text into speech using Gemini, ElevenLabs, or OpenAI TTS backends.
npx skills add https://github.com/michaelboeding/skills --skill voice-generation
Please help me install this Agent Skill. Skill: voice-generation Source: https://github.com/michaelboeding/skills/tree/main/skills/voice-generation Command: npx skills add https://github.com/michaelboeding/skills --skill voice-generation
Turning written text into natural-sounding speech is time-consuming and requires specialized software or manual recording. This Skill streamlines the process by providing a pluggable TTS workflow that supports multiple backends.
Use the voice-generation skill to convert a short paragraph into speech with your preferred backend. Example: Generate narration using Gemini TTS with voice Kore.
High-intent search queries and answers about installing and using this skill.
Text-to-speech converts written content into natural-sounding audio using AI backends like Gemini TTS, ElevenLabs, or OpenAI TTS. This Skill automates the conversion process, letting you generate podcast episodes, audiobook narration, or video voiceovers by providing text and selecting your preferred voice and output format.
This Skill supports three TTS backends: Google Gemini TTS, ElevenLabs, and OpenAI TTS. Each backend offers different voice quality, language coverage, and voice-cloning capabilities, so you can choose based on your project needs and API availability.
Yes. The Skill supports both single- and multi-speaker generation, allowing you to create dialogue, character voices, or narration with distinct speakers by specifying different voices for different text segments.
The Skill saves generated audio to disk with configurable formats, giving you flexibility in file type and quality settings. You can customize the output format to match your platform, delivery channel, or archival requirements.
Yes. The Skill enforces API key availability for your chosen TTS backend—Gemini, ElevenLabs, or OpenAI. You must provide valid credentials for the backend you select before generating speech.
Beyond podcasts, TTS handles video narration, accessibility prompts for visually impaired users, character dialogue for scripts and games, and automated content narration. This Skill's multi-backend workflow makes it practical for any scenario requiring natural-sounding spoken audio from text.
hasnaGenerate MP3 audio from text using ElevenLabs, OpenAI TTS, or Google Text-to-Speech.
KaiserWhoLearnsExtract, normalize, and mix audio from video files using FFmpeg commands.
hmzainjamilAutomate podcast production and distribution from recording assets to published episodes.
curiositechGenerate speech with ElevenLabs and process audio to broadcast loudness standards.
