Can I control the accent and emotion of the AI voice?

Absolutely. When using Gemini TTS, you can provide natural language instructions like 'say cheerfully with a British accent' to influence the output.

Can I generate dialogues with multiple speakers?

Yes, using the Google Gemini TTS provider, you can generate multi-speaker scripts with up to two different voices in a single execution.

What audio formats does the skill produce?

The output format depends on the provider used, but typically includes high-quality WAV, MP3, Opus, AAC, or FLAC files.

Which AI voice providers are supported?

This skill supports Google Gemini TTS, ElevenLabs, and OpenAI TTS, allowing you to choose the best provider based on quality, cost, or specific features like voice cloning.

Do I need my own API keys to use this skill?

Yes, you will need at least one valid API key from Google (Gemini), ElevenLabs, or OpenAI to authenticate the requests and generate audio.

AI Voice Generation

Name: AI Voice Generation
Author: michaelboeding

bymichaelboeding

•

Gestión de Contenido

Generates high-quality, realistic AI speech and multi-speaker narration using Google Gemini, ElevenLabs, and OpenAI text-to-speech APIs.

This skill integrates professional-grade text-to-speech capabilities directly into your AI workflow, allowing you to synthesize natural-sounding audio for podcasts, tutorials, and automated voiceovers. It offers unique flexibility by supporting three major providers: Google Gemini for multi-speaker dialogues and style control, ElevenLabs for industry-leading voice cloning and quality, and OpenAI for fast, reliable narration. Whether you need a specific regional accent, a cheerful marketing tone, or a complex two-person script, this skill handles the text optimization and API execution to deliver production-ready audio files.

Características Principales

01Native multi-speaker dialogue support for up to two voices

02Automatic text preprocessing for improved pronunciation and rhythm

03Natural language style control for accents, tone, and pacing

04High-fidelity voice cloning and access to 100+ pre-made voices

059 GitHub stars

06Multi-provider integration with Google Gemini, ElevenLabs, and OpenAI

Casos de Uso

01Generating high-quality audiobooks with consistent character voices

02Creating professional narrations for marketing videos and tutorials

03Automating podcast production with multi-character dialogues

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add michaelboeding/skills voice-generation

For use in Claude.ai and ChatGPT

Download Skill