Gemini Audio

What it does

When your agent uses it

• Processing audio files
• Creating transcripts
• Analyzing speech/music/sounds
• Generating natural speech from text

Example prompts

• “/gemini-audio”

Requirements

• Python 3
• A credential in GEMINI_API_KEY
• Pre-approved tools (allowed-tools): Bash, Read, Write, Edit

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Process environment: export GEMINI_API_KEY="your-key"
2. 2Skill directory: .claude/skills/gemini-audio/.env
3. 3Project directory: ./.env (project root)

What it can do on your machine

Read from SKILL.md and the folder at commit c6c0686. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Write
  • Edit

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 5 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • pip

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • ai.google.dev
  • aistudio.google.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • GEMINI_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gemini Audio loads about 2k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 551 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~83

When it runs · the whole SKILL.md, loaded when a task matches

~2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:33

  irectory**: `.claude/skills/gemini-audio/.env`

• NoteMentions a .env fileSKILL.md:34

  3. **Project directory**: `./.env` (project root)

• NoteMentions a .env fileSKILL.md:38

  Create `.env` file with:

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Write, Edit

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from einverne/dotfiles at commit c6c0686, republished under its MIT licence (© einverne). 551 words, ~2,010 tokens.

name

gemini-audio

description

Guide for implementing Google Gemini API audio capabilities - analyze audio with transcription, summarization, and understanding (up to 9.5 hours), plus generate speech with controllable TTS. Use when processing audio files, creating transcripts, analyzing speech/music/sounds, or generating natural speech from text.

allowed-tools

Bash, Read, Write, Edit

license

MIT

GEMINI_API_KEY=your_api_key_here

pip install google-genai

from google import genai
import os

# API key auto-detected from environment
client = genai.Client(api_key=os.getenv('GEMINI_API_KEY'))

# Upload audio file
myfile = client.files.upload(file='podcast.mp3')

# Transcribe
response = client.models.generate_content(
    model='gemini-2.5-flash',
    contents=['Generate a transcript of the speech.', myfile]
)
print(response.text)

# Summarize
response = client.models.generate_content(
    model='gemini-2.5-flash',
    contents=['Summarize the key points in 5 bullets.', myfile]
)
print(response.text)

# Transcribe audio
python .claude/skills/gemini-audio/scripts/transcribe.py audio.mp3

# Summarize audio
python .claude/skills/gemini-audio/scripts/analyze.py audio.mp3 \
  "Summarize key points"

# Analyze specific segment (timestamps in MM:SS format)
python .claude/skills/gemini-audio/scripts/analyze.py audio.mp3 \
  "What is discussed from 02:30 to 05:15?"

# Generate speech
python .claude/skills/gemini-audio/scripts/generate-speech.py \
  "Welcome to our podcast" \
  --output welcome.wav

response = client.models.generate_content(
    model='gemini-2.5-flash-native-audio-preview-09-2025',
    contents='Generate audio: Welcome to today\'s episode, in a warm, friendly tone.'
)

# Save audio output
with open('output.wav', 'wb') as f:
    f.write(response.audio_data)

# Upload and reuse
myfile = client.files.upload(file='large-audio.mp3')

# Use file multiple times
response1 = client.models.generate_content(
    model='gemini-2.5-flash',
    contents=['Transcribe this', myfile]
)

response2 = client.models.generate_content(
    model='gemini-2.5-flash',
    contents=['Summarize this', myfile]
)

from google.genai import types

with open('small-audio.mp3', 'rb') as f:
    audio_bytes = f.read()

response = client.models.generate_content(
    model='gemini-2.5-flash',
    contents=[
        'Describe this audio',
        types.Part.from_bytes(data=audio_bytes, mime_type='audio/mp3')
    ]
)

python scripts/transcribe.py meeting.mp3 --include-timestamps

python scripts/analyze.py interview.wav "Extract main topics and key quotes"

python scripts/analyze.py discussion.mp3 "Identify speakers and extract dialogue"

python scripts/analyze.py podcast.mp3 "Summarize content from 10:30 to 15:45"

python scripts/analyze.py ambient.wav "Identify all sounds: voices, music, ambient"

© einverne, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (scripts, references) in claude/skills/gemini-audio of einverne/dotfiles.

• SKILL.md
• .env.example
• references/README.md
• references/api-reference.md
• references/best-practices.md
• references/code-examples.md
• references/tts-guide.md
• scripts/analyze.py
• scripts/api_key_helper.py
• scripts/generate-speech.py
• scripts/manage-files.py
• scripts/transcribe.py

Open the folder on GitHubat commit c6c0686