gemini-tts-fast

Convert text to WAV narration at 1.2x speed via Google Gemini TTS API.

3|2|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/joyehuang/skills --skill gemini-tts-fast
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-tts-fast
Source: https://github.com/joyehuang/skills/tree/main/gemini-tts-fast
Command: npx skills add https://github.com/joyehuang/skills --skill gemini-tts-fast

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, ffmpeg.

What problem does it solve?

This skill solves the bottleneck of generating natural-sounding, high-quality voiceovers for video content while maintaining a consistent, efficient production pace.

Core Features & Use Cases

  • Fixed 1.2x playback speed optimized for engaging video narration.
  • Supports multiple voice profiles including Puck, Charon, and Aoede.
  • Automatic conversion of raw Gemini TTS output into standard WAV files using ffmpeg.
  • Use Case: Quickly convert a written video script into a series of narration audio files for a project, ensuring all clips are perfectly timed for a dynamic viewing experience.

Quick Start

Use the gemini-tts-fast skill to convert the text Hello world into an audio file named output.wav at 1.2x speed.

Frequently Asked Questions about gemini-tts-fast

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate high-speed video narration from text using the Gemini TTS API?

To generate high-speed video narration from text, the Skill uses the Google Gemini TTS API to synthesize speech and processes it with ffmpeg to output a standard WAV file at a fixed 1.2x playback speed.

Can I convert Gemini TTS output to WAV format with a faster playback speed for videos?

Yes, you can convert Gemini TTS output to standard WAV format with faster playback. The Skill automatically applies ffmpeg audio processing to adjust the speed to a fixed 1.2x rate optimized for video narration.

Do I need ffmpeg and google-genai installed to run automated text to speech conversion?

Yes, you need both ffmpeg and google-genai installed in your Python environment. The google-genai framework handles the text to speech API calls, while ffmpeg performs the required audio processing and speed adjustment.

What voice profiles are available for generating professional audio voiceovers?

The available voice profiles for generating professional audio voiceovers include Puck, Charon, and Aoede. These options provide varied tones to match your video production workflow.

Is fixed-speed narration better than variable-speed audio for video production workflows?

Fixed-speed narration at 1.2x provides a consistent, efficient production pace for video production workflows, ensuring all audio clips are perfectly timed for a dynamic viewing experience without manual speed adjustments.