Audio Script Writer

Audio Script Writer

Overview

Content transformation tool that converts written medical and scientific materials into professionally structured audio scripts suitable for podcasts, educational videos, audiobooks, and voiceover narration.

Key Capabilities:

When to Use

✅ Use this skill when:

❌ Do NOT use when:

Integration:

Core Capabilities

1. Spoken Word Transformation

Convert written text to conversational audio style:

from scripts.audio_writer import AudioScriptWriter
writer = AudioScriptWriter()
Transform written content
script = writer.convert_to_audio(
    source_text=research_paper,
    format="podcast",  # podcast, video, lecture, audiobook
    target_audience="medical_students",
    duration_minutes=15
)
print(script.spoken_text)
Converts: "The pathophysiology of diabetes mellitus involves..."
To: "So what exactly happens in diabetes? Well, it all starts when..."

Transformation Rules: | Written Style | Audio Style | Example | |---------------|-------------|---------| | "Furthermore" | "Plus" | Less formal transitions | | " et al." | "and their colleagues" | Expand abbreviations | | Numbers in text | Spoken numbers | "15%" → "15 percent" | | Long sentences | 15-20 word max | Break into digestible chunks | | Passive voice | Active voice | "was observed" → "we saw" | | Citations | Omit or footnote | "(Smith et al., 2024)" → [reference tone] |

2. Pronunciation Guide Generation

Create phonetic spelling for medical terms:

# Generate pronunciation guide
pronunciation = writer.create_pronunciation_guide(
    text=script,
    include_phonetic=True,
    include_syllables=True
)
Output:
"Hyperlipidemia: hi-per-lip-i-DEE-mee-uh"
"Metformin: met-FOR-min"
"Atherosclerosis: ath-er-oh-skleh-ROH-sis"

Guide Elements:

3. Timing and Pacing

Calculate speaking duration and mark pacing cues:

# Analyze timing
timing = writer.calculate_timing(
    script=script,
    speaking_rate="conversational",  # slow, conversational, fast
    include_pauses=True
)
print(f"Estimated duration: {timing.duration_minutes} minutes")
print(f"Word count: {timing.word_count}")
print(f"Pace: {timing.words_per_minute} WPM")

Speaking Rates: | Style | WPM | Use Case | |-------|-----|----------| | Slow/Educational | 120-130 | Patient education, complex topics | | Conversational | 140-160 | Podcasts, general audience | | Fast/News | 170-190 | Time-constrained content | | Variable | Varies | Dynamic pacing with pauses |

Pacing Cues:

[BREATHE] - Brief pause for narrator
[PAUSE 2s] - Two-second pause for emphasis
[SLOW DOWN] - Reduce pace for key point
[SPEED UP] - Increase energy/excitement
[BEAT] - Dramatic pause

4. Multi-Format Templates

Generate scripts for different audio formats:

# Podcast episode
podcast = writer.create_podcast_script(
    content=article,
    episode_format="interview",  # solo, interview, panel
    include_intro_music=True,
    ad_breaks=[5, 12]  # minutes
)
Educational video
video = writer.create_video_script(
    content=lecture_slides,
    visual_cues=True,  # Mark where visuals change
    b_roll_notes=True  # Suggest supplemental footage
)

Format Types: | Format | Characteristics | Best For | |--------|-----------------|----------| | Podcast | Conversational, segments, ads | Long-form content, interviews | | Video | Visual cues, B-roll notes | YouTube, educational platforms | | Lecture | Structured, Q&A breaks | Online courses, training | | Audiobook | Chapter markers, consistent tone | Textbooks, memoirs | | News | Tight, factual, quick | Research briefs, updates |

Common Patterns

Pattern 1: Research Paper to Podcast

Scenario: Convert published study to 15-minute podcast episode.

# Convert paper to podcast script
python scripts/main.py \
  --input paper.pdf \
  --format podcast \
  --duration 15 \
  --style conversational \
  --include-intro-outro \
  --output podcast_script.txt
Generate pronunciation guide
python scripts/main.py \
  --input podcast_script.txt \
  --generate-pronunciation \
  --output pronunciation_guide.txt

Structure:

[INTRO MUSIC 5s]
HOST: Welcome to Medical Research Today. I'm your host...
[BREATHE]
HOST: Today we're diving into a fascinating study about...
[PAUSE]
HOST: So what did the researchers find? Well...
[BREATHE]
HOST: Dr. Smith, one of the study authors, explains...
[SOUND BITE: Interview clip]
...
[OUTRO MUSIC]

Pattern 2: Medical Lecture Recording

Scenario: Convert lecture notes to video script for online course.

# Create lecture script
lecture = writer.create_lecture_script(
    notes=lecture_content,
    duration=45,  # minutes
    break_intervals=[15, 30],  # minutes for student breaks
    interaction_points=True  # "Pause and think..." prompts
)
Add visual cues
script = writer.add_visual_cues(
    script=lecture,
    slide_transitions=True,
    animation_notes=True
)

Lecture Elements:

Pattern 3: Patient Education Audio

Scenario: Create audio guide for diabetes management.

# Patient-friendly script
patient_script = writer.create_patient_script(
    medical_content=diabetes_guide,
    reading_level=6,  # 6th grade
    empathetic_tone=True,
    key_points_highlighted=True
)
Slow, clear pacing
patient_script.adjust_pacing(
    wpm=130,
    pause_after_sentences=1.5  # seconds
)

Patient Script Features:

Pattern 4: Conference Presentation to Video

Scenario: Adapt live presentation to YouTube video format.

# Convert presentation script
python scripts/main.py \
  --input presentation_transcript.txt \
  --format video \
  --platform youtube \
  --include-hooks true \
  --engagement-cues true \
  --output youtube_script.txt

YouTube Optimization:

Complete Workflow Example

From research paper to published podcast:

# Step 1: Extract and summarize content
python scripts/main.py \
  --input paper.pdf \
  --extract-key-points \
  --output key_points.txt
Step 2: Convert to audio script
python scripts/main.py \
  --input key_points.txt \
  --format podcast \
  --duration 20 \
  --output raw_script.txt
Step 3: Add production elements
python scripts/main.py \
  --input raw_script.txt \
  --add-music-cues \
  --add-sound-effects \
  --add-pacing-marks \
  --output production_script.txt
Step 4: Generate pronunciation guide
python scripts/main.py \
  --input production_script.txt \
  --generate-pronunciation \
  --output pronunciations.txt
Step 5: Create timing breakdown
python scripts/main.py \
  --input production_script.txt \
  --calculate-timing \
  --output timing_breakdown.txt

Python API:

from scripts.audio_writer import AudioScriptWriter
from scripts.pronunciation import PronunciationGuide
from scripts.timing import TimingCalculator
Initialize
writer = AudioScriptWriter()
pronouncer = PronunciationGuide()
timing = TimingCalculator()
Read source material
with open("research_article.txt", "r") as f:
    content = f.read()
Step 1: Convert to spoken format
script = writer.convert_to_audio(
    text=content,
    format="podcast",
    target_duration=15,  # minutes
    audience="general_medical"
)
Step 2: Add production elements
script_with_cues = writer.add_production_cues(
    script=script,
    music_stings=True,
    transition_effects=True
)
Step 3: Generate pronunciation guide
medical_terms = pronouncer.extract_terms(script_with_cues)
pronunciation_guide = pronouncer.create_guide(medical_terms)
Step 4: Calculate timing
timing_analysis = timing.calculate(
    script=script_with_cues,
    speaking_rate=150  # WPM
)
Export complete production package
writer.export_production_package(
    script=script_with_cues,
    pronunciation=pronunciation_guide,
    timing=timing_analysis,
    output_dir="podcast_production/"
)

Quality Checklist

Content Quality:

Audio Optimization:

Production Quality:

Before Recording:

Common Pitfalls

Content Issues:

Audio Issues:

Production Issues:

References

Available in references/ directory:

Scripts

Located in scripts/ directory:

Limitations

Parameters

| Parameter | Type | Default | Required | Description | |-----------|------|---------|----------|-------------| | --input, -i | string | - | No | Input text file path | | --output, -o | string | - | No | Output JSON file path (default: stdout) | | --text | string | - | No | Direct text input (alternative to --input) | | --duration, -d | int | 5 | No | Target duration in minutes | | --pace, -p | string | normal | No | Speaking pace (slow, normal, fast) | | --style, -s | string | conversational | No | Script style (conversational, formal, educational) |

Usage

Basic Usage

# Convert from file
python scripts/main.py --input article.txt --duration 5 --output script.json
Direct text input
python scripts/main.py --text "Medical research findings..." --duration 3
From stdin
cat article.txt | python scripts/main.py --duration 5 --style conversational
With specific style and pace
python scripts/main.py --input paper.txt --style educational --pace slow

Risk Assessment

| Risk Indicator | Assessment | Level | |----------------|------------|-------| | Code Execution | Python script executed locally | Low | | Network Access | No external API calls | Low | | File System Access | Read input files, write output files | Low | | Instruction Tampering | Standard prompt guidelines | Low | | Data Exposure | Output saved only to specified location | Low |

Security Checklist

Prerequisites

# Python 3.7+
No additional packages required (uses standard library)

Evaluation Criteria

Success Metrics

Test Cases

Lifecycle Status

🎙️ Pro Tip: The best audio scripts sound natural when spoken. Always read your script aloud before finalizing—if you stumble over a sentence, your narrator will too. Revise for the ear, not the eye.

Basic Usage

# Convert from file
python scripts/main.py --input article.txt --duration 5 --output script.json
Direct text input
python scripts/main.py --text "Medical research findings..." --duration 3
From stdin
cat article.txt | python scripts/main.py --duration 5 --style conversational
With specific style and pace
python scripts/main.py --input paper.txt --style educational --pace slow

# Python 3.7+
No additional packages required (uses standard library)