skills.rest
Panastra-labs
Panastra-labsOFFICIAL
Explore all skills by this author →
GitHub

gemini-tts

Generate 24 kHz 16-bit mono WAV voiceover audio from text.

Updated Feb 25, 2026
Search Tags:#text-to-speech#gemini#tts#voiceover#audio-generation#multi-speaker#duration-measurement
One-click install
npx skills add https://github.com/Panastra-labs/skills --skill gemini-tts-panastra-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-tts
Source: https://github.com/Panastra-labs/skills/tree/main/gemini-tts
Command: npx skills add https://github.com/Panastra-labs/skills --skill gemini-tts-panastra-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the creation of high-quality AI voiceover audio from plain text so teams can produce narration, dialogue, and multilingual voice tracks without manual recording or complex audio tooling.

Core Features & Use Cases

  • Generate speech: Produce 24 kHz, 16-bit mono WAV audio from text using Gemini TTS.
  • Multi-speaker dialogue: Create two-speaker conversations with per-speaker voice selection and style control.
  • Asset tooling: Measure exact durations, inspect audio quality and pronunciation, and iterate by chunking to meet timeline targets.
  • Use Case: Create podcast snippets, video narration, character dialogue for games, or timed voiceover tracks for editor timelines.

Quick Start

Call the generate_speech function with your script text and optional voice_name or speakers to save a WAV audio file (for example, call generate_speech with text set to Welcome to our product tour).

Frequently Asked Questions about gemini-tts

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

FAQPage Schema
How do I generate two-speaker dialogue audio from text for a podcast?▼

To generate two-speaker dialogue audio, call the generate_speech function with your script text and configure multi-speaker settings with per-speaker voice selection. It outputs 24 kHz 16-bit mono WAV files.

Can I use Gemini TTS to create timed voiceover tracks for video editor timelines?▼

Yes, Gemini TTS supports timeline-synced chunks for video narration. You can iterate by chunking text to meet timeline targets and inspect exact durations to sync audio with your editor.

What's the best way to measure audio duration and inspect pronunciation in AI voiceover generation?▼

Use the provided asset tooling functions to measure exact durations and inspect audio quality. This allows you to verify pronunciation and iterate on text chunks to meet timeline targets.

Does the gemini-2.5-flash-preview-tts model support multilingual voiceover scripts?▼

Yes, the gemini-2.5-flash-preview-tts model supports multilingual scripts. You can generate professional voiceover audio from plain text in multiple languages for narration and dialogue.

What are the limitations for multi-speaker configs in Gemini TTS?▼

The limitation for multi-speaker configs is a maximum of two speakers. It supports both gemini-2.5-flash-preview-tts and gemini-2.5-pro-preview-tts models for generating two-speaker conversations.

Do I need python-dotenv to generate AI voiceover audio with Gemini TTS?▼

Yes, you need python-dotenv and google-genai dependencies installed. These allow the Skill to authenticate and generate 24 kHz 16-bit mono WAV audio files from your text.

Related Skills

Explore More Content & Communication Skills→
Svenja-devSvenja-dev
38

gemini-image-gen

Generate branded images from prompts using Google's Gemini API.

Community
Intermediate
synqingsynqing
15

SPH0645-Microphone-Integration

Convert SPH0645 PDM audio to PCM data for ESP32 DSP processing.

Community
Intermediate
ToqsickToqsick

audiobook

Convert text into audiobooks with multi-character voiceover and dialogue segmentation.

Community
Advanced
OpenRouterTeamOpenRouterTeam
209

openrouter-tts

Convert written text into speech audio via OpenRouter's TTS API.

Official
Intermediate