NeelakshSaxena/Drishti / .agents/skills/ai-multimodal
ai-multimodal
VerifiedProcess and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.
| File | Kind | Size |
|---|---|---|
| .env.example | other | 7.3 KB |
| SKILL.md | skill md | 5.6 KB |
| references/audio-processing.md | markdown | 9.5 KB |
| references/image-generation.md | markdown | 18.1 KB |
| references/video-analysis.md | markdown | 11.6 KB |
| references/video-generation.md | markdown | 10.8 KB |
| references/vision-understanding.md | markdown | 10.8 KB |
| scripts/check_setup.py | script | 8.5 KB |
| scripts/document_converter.py | script | 12.2 KB |
| scripts/gemini_batch_process.py | script | 37.2 KB |
| scripts/media_optimizer.py | script | 16.1 KB |
| scripts/requirements.txt | manifest | 442 B |
| scripts/tests/requirements.txt | manifest | 352 B |
| scripts/tests/test_document_converter.py | script | 2.2 KB |
| scripts/tests/test_gemini_batch_process.py | script | 12.4 KB |
| scripts/tests/test_media_optimizer.py | script | 11.5 KB |
references/audio-processing.md
View on GitHub# Audio Processing Reference
Comprehensive guide for audio analysis and speech generation using Gemini API.
## Audio Understanding
### Supported Formats
| Format | MIME Type | Best Use |
|--------|-----------|----------|
| WAV | `audio/wav` | Uncompressed, highest quality |
| MP3 | `audio/mp3` | Compressed, widely compatible |
| AAC | `audio/aac` | Compressed, good quality |
| FLAC | `audio/flac` | Lossless compression |
| OGG Vorbis | `audio/ogg` | Open format |
| AIFF | `audio/aiff` | Apple format |
### Specifications
- **Maximum length**: 9.5 hours per request
- **Multiple files**: Unlimited count, combined max 9.5 hours
- **Token rate**: 32 tokens/second (1 minute = 1,920 tokens)
- **Processing**: Auto-downsampled to 16 Kbps mono
- **File size limits**:
- Inline: 20 MB max total request
- File API: 2 GB per file, 20 GB project quota
- Retention: 48 hours auto-delete
## Transcription
### Basic Transcription
```python
from google import genai
import os
client = genai.Client(api_key=os.getenv('GEMINI_API_KEY'))
# Upload audio
myfile = client.files.upload(file='meeting.mp3')
# Transcribe
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Generate a transcript of the speech.', myfile]
)
print(response.text)
```
### With Timestamps
```python
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Generate transcript with timestamps in MM:SS format.', myfile]
)
```
### Multi-Speaker Identification
```python
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Transcribe with speaker labels. Format: [Speaker 1], [Speaker 2], etc.', myfile]
)
```
### Segment-Specific Transcription
```python
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Transcribe only the segment from 02:30 to 05:15.', myfile]
)
```
## Audio Analysis
### Summarization
```python
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Summarize key points in 5 bullets with timestamps.', myfile]
)
```
### Non-Speech Audio Analysis
```python
# Music analysis
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Identify the musical instruments and genre.', myfile]
)
# Environmental sounds
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Identify all sounds: voices, music, ambient noise.', myfile]
)
# Birdsong identification
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Identify bird species based on their calls.', myfile]
)
```
### Timestamp-Based Analysis
```python
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['What is discussed from 10:30 to 15:45? Provide key points.', myfile]
)
```
## Input Methods
### File Upload (>20MB or Reuse)
```python
# Upload once, use multiple times
myfile = client.files.upload(file='large-audio.mp3')
# First query
response1 = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Transcribe this', myfile]
)
# Second query (reuses same file)
response2 = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Summarize this', myfile]
)
```
### Inline Data (<20MB)
```python
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')
]
)
```
## Speech Generation (TTS)
### Available Models
| Model | Quality | Speed | Cost/1M tokens |
|-------|---------|-------|----------------|
| `gemini-2.5-flash-native-audio-preview-09-2025` | High | Fast | $10 |
| `gemini-2.5-pro` TTS mode | Premium | Slower | $20 |
### Basic TTS
```python
response = client.models.generate_content(
model='gemini-2.5-flash-native-audio-preview-09-2025',
contents='Generate audio: Welcome to today\'s episode.'
)
# Save audio
with open('output.wav', 'wb') as f:
f.write(response.audio_data)
```
### Controllable Voice Style
```python
# Professional tone
response = client.models.generate_content(
model='gemini-2.5-flash-native-audio-preview-09-2025',
contents='Generate audio in a professional, clear tone: Welcome to our quarterly earnings call.'
)
# Casual and friendly
response = client.models.generate_content(
model='gemini-2.5-flash-native-audio-preview-09-2025',
contents='Generate audio in a friendly, conversational tone: Hey there! Let\'s dive into today\'s topic.'
)
# Narrative style
response = client.models.generate_content(
model='gemini-2.5-flash-native-audio-preview-09-2025',
contents='Generate audio in a narrative, storytelling tone: Once upon a time, in a land far away...'
)
```
### Voice Control Parameters
- **Style**: Professional, casual, narrative, conversational
- **Pace**: Slow, normal, fast
- **Tone**: Friendly, serious, enthusiastic
- **Accent**: Natural language control (e.g., "British accent", "Southern drawl")
## Best Practices
### File Management
1. Use File API for files >20MB
2. Use File API for repeated queries (saves tokens)
3. Files auto-delete after 48 hours
4. Clean up manually when done:
```python
client.files.delete(name=myfile.name)
```
### Prompt Engineering
**Effective prompts**:
- "Transcribe from 02:30 to 03:29 in MM:SS format"
- "Identify speakers and extract dialogue with timestamps"
- "Summarize key points with relevant timestamps"
- "Transcribe and analyze sentiment for each speaker"
**Context improves accuracy**:
- "This is a medical interview - use appropriate terminology"
- "Transcribe this legal deposition with precise terminology"
- "This is a technical podcast about machine learning"
**Combined tasks**:
- "Transcribe and summarize in bullet points"
- "Extract key quotes with timestamps and speaker labels"
- "Transcribe and identify action items with timestamps"
### Cost Optimization
**Token calculation**:
- 1 minute audio = 1,920 tokens
- 1 hour audio = 115,200 tokens
- 9.5 hours = 1,094,400 tokens
**Model selection**:
- Use `gemini-2.5-flash` ($1/1M tokens) for most tasks
- Upgrade to `gemini-2.5-pro` ($3/1M tokens) for complex analysis
- For high-volume: `gemini-1.5-flash` ($0.70/1M tokens)
**Reduce costs**:
- Process only relevant segments using timestamps
- Use lower-quality audio when possible
- Batch multiple short files in one request
- Cache context for repeated queries
### Error Handling
```python
import time
def transcribe_with_retry(file_path, max_retries=3):
"""Transcribe audio with exponential backoff retry"""
for attempt in range(max_retries):
try:
myfile = client.files.upload(file=file_path)
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Transcribe with timestamps', myfile]
)
return response.text
except Exception as e:
if attempt == max_retries - 1:
raise
wait_time = 2 ** attempt
print(f"Retry {attempt + 1} after {wait_time}s")
time.sleep(wait_time)
```
## Common Use Cases
### 1. Meeting Transcription
```python
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=[
'''Transcribe this meeting with:
1. Speaker labels
2. Timestamps for topic changes
3. Action items highlighted
''',
myfile
]
)
```
### 2. Podcast Summary
```python
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=[
'''Create podcast summary with:
1. Main topics with timestamps
2. Key quotes from each speaker
3. Recommended episode highlights
''',
myfile
]
)
```
### 3. Interview Analysis
```python
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=[
'''Analyze interview:
1. Questions asked with timestamps
2. Key responses from interviewee
3. Overall sentiment and tone
''',
myfile
]
)
```
### 4. Content Verification
```python
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=[
'''Verify audio content:
1. Check for specific keywords or phrases
2. Identify any compliance issues
3. Note any concerning statements with timestamps
''',
myfile
]
)
```
### 5. Multilingual Transcription
```python
# Gemini auto-detects language
response = client.models.generate_content(
model='gemini-2.5-flash',
contents=['Transcribe this audio and translate to English if needed.', myfile]
)
```
## Token Costs
**Audio Input** (32 tokens/second):
- 1 minute = 1,920 tokens
- 10 minutes = 19,200 tokens
- 1 hour = 115,200 tokens
- 9.5 hours = 1,094,400 tokens
**Example costs** (Gemini 2.5 Flash at $1/1M):
- 1 hour audio: 115,200 tokens = $0.12
- Full day podcast (8 hours): 921,600 tokens = $0.92
## Limitations
- Maximum 9.5 hours per request
- Auto-downsampled to 16 Kbps mono (quality loss)
- Files expire after 48 hours
- No real-time streaming support
- Non-speech audio less accurate than speech
---
## Related References
**Current**: Audio Processing
**Related Capabilities**:
- [Video Analysis](./video-analysis.md) - Extract audio from videos
- [Video Generation](./video-generation.md) - Generate videos with native audio
- [Image Understanding](./vision-understanding.md) - Analyze audio with visual context
**Back to**: [AI Multimodal Skill](../SKILL.md)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |