gemini-audio

Process audio into transcripts, summaries, and speech via the Google Gemini API.

Updated Sep 16, 2025

Search Tags:#transcription #audio #gemini #tts #podcasts #speech-generation

Ready to run

npx skills add https://github.com/kienhaminh/speed-reader --skill gemini-audio-kienhaminh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gemini-audio
Source: https://github.com/kienhaminh/speed-reader/tree/main/.claude/skills/gemini-audio
Command: npx skills add https://github.com/kienhaminh/speed-reader --skill gemini-audio-kienhaminh

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates end-to-end audio workflows: transcription with timestamps, content analysis (speech, music, environment), and text-to-speech generation, enabling scalable podcast, meeting, and media analysis at scale.

Core Features & Use Cases

Transcription: Accurate transcripts with optional timestamps.
Audio Analysis: Identify speakers, topics, and non-speech sounds.
Speech Synthesis (TTS): Generate natural speech from text with controllable voice traits.
Production Workflows: Streamline podcast post-production, interviews, webinars.

Quick Start

Run the provided Python helper scripts to transcribe an audio file, then summarize or generate speech.

Frequently Asked Questions about gemini-audio

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

FAQPage Schema

How do I transcribe audio files with timestamps using the Gemini API?▼

Transcribe audio with timestamps by uploading your file to the Gemini API, which processes formats like MP3, WAV, and OGG up to 9.5 hours per request and returns timestamped transcripts with speaker attribution and optional content summaries.

Can I analyze podcasts and meetings for speakers, topics, and sounds with Gemini?▼

Yes, Gemini audio analysis identifies speakers, topics, speech patterns, music, and environmental sounds in long-form content like podcasts, interviews, and webinars, producing structured summaries and speaker attribution.

What audio formats and languages does Gemini transcription support?▼

Gemini supports multiple audio formats including MP3, WAV, OGG, and others, with multi-language transcription capability enabling workflows across global podcasts, interviews, and lectures in any language.

How do I generate natural speech from text using Gemini text-to-speech?▼

Generate speech synthesis from text using Gemini's TTS with controllable voice traits and output formats, enabling podcast production, automated narration, and media workflows with configurable models and API key management.

Do I need to upload audio files or can I use inline data with Gemini?▼

Gemini supports both file uploads and inline audio data, handling up to 9.5 hours per request and working with local files or streaming data, enabling flexible integration into production podcast and meeting analysis pipelines.

What's the best way to automate podcast post-production workflows with audio processing?▼

Automate podcast post-production by chaining transcription with timestamps, content analysis for speakers and topics, and text-to-speech generation using configurable Gemini prompts and Vertex AI or AI Studio API management.