- Home
- Skills
- Writing & Content
- Voiceover Script Timer
Works with the AI Agents you already use
Voiceover Script Timer
Time scripts, fit ad reads to strict durations, and export SSML for voiceover and TTS production.
$2.99
Voiceover Script Timer
Example session with this skill installed
Estimate the time for this explainer script and fit it to 30 seconds: "Our API handles 500 requests per second. It integrates with AWS, GCP, and Azure. Deploy in minutes, not days."
- Read your context and instructions
- Compiled the voiceover script timer
I have analyzed your script using the 'explainer' style (150 WPM). The original script is approximately 22 words and takes 9 seconds to read at a steady pace. To fill a 30-second slot, you need to expand the content or slow the delivery significantly.
Script Timing Analysis
| Metric | Value |
|---|---|
| Current Word Count | 22 words |
| Current Estimated Duration | 8.8 seconds |
| Target Duration | 30.0 seconds |
| Required Adjustment | Add ~53 words or slow to 44 WPM |
| Complexity Flags | "AWS, GCP, and Azure" (Acronym cluster - slow down) |
Recommended Expansion for 30s
"Our powerful API easily handles over 500 requests every single second, providing the scale your business needs. It integrates directly with your existing infrastructure on AWS, GCP, and Azure. With our streamlined setup, your team can deploy the full system in just a few minutes, rather than waiting for days of configuration."
SSML Export
<speak>
<p>
<s duration="4000ms">Our API handles 500 requests per second.</s>
<break time="500ms"/>
<s duration="3000ms">It integrates with <emphasis level="moderate">AWS, GCP, and Azure.</emphasis></s>
<break time="500ms"/>
<s duration="2000ms">Deploy in minutes, not days.</s>
</p>
</speak>
Next steps
- Record a scratch track to verify if the 44 WPM pace feels natural or too sluggish.
- Use the expanded script version if you need to fill the full 30-second broadcast slot.
- Run the SSML export through your preferred TTS engine to check pronunciation of the acronyms.
Connects securely to your tools. The creator never sees your data.
About this skill
Writing scripts that run too long or too short wastes production time and ruins pacing. This skill calculates precise spoken duration for voiceover, narration, and ad reads, ensuring your copy fits your time slots perfectly.
What it does
- Duration estimation calculates timing per paragraph and total script length based on specific speaking styles.
- Dynamic rate mapping applies industry-standard speeds for conversational, explainer, ad read, audiobook, and trailer formats.
- Script fitting identifies necessary cuts or pace adjustments to hit target durations like 15, 30, or 60-second spots.
- Speech optimization flags tongue-twisters, complex clusters, and overly long sentences that cause recording stumbles.
- SSML generation exports ready-to-use markup with breaks and emphasis for text-to-speech workflows.
How it works
- Analyze the input script to expand abbreviations and numbers into spoken words for accurate word counts.
- Apply a specific speaking style or custom WPM rate to determine the estimated runtime.
- Compare the output against a target time to generate a list of required edits or pacing warnings.
- Export the processed script as plain text with timestamps or as an SSML file for TTS engines.
Frameworks & tools
The tool uses Python for script processing and handles standard text files. It outputs raw text, timed logs, and SSML files compatible with AWS Polly, Google Cloud TTS, and Azure Speech.
Why this beats prompting it yourself
Standard LLM prompts often hallucinate word-to-minute ratios and fail to account for the physical time it takes to pronounce complex abbreviations. This skill uses specific rate math and phonetic density checks to give you a result that actually holds up in the recording booth.
Use cases
- Fit a 72-second sponsor read into a strict 60-second podcast ad slot.
- Estimate the total runtime of a non-fiction audiobook for production planning.
- Identify "mouth-feel" issues in explainer video scripts before the VO talent arrives.
- Generate SSML tags for a help center documentation video series.
Known limitations
Does not account for non-verbal performance elements like character acting or specific dramatic pauses unless manually specified. Accuracy depends on the speaker matching the selected WPM rate.
Requires a Python environment to run the underlying script. Timing accuracy is an estimate based on average speaking rates and may vary with individual performance styles.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago