Best practices for creating AI audio
This is a guide for anyone who uses the AI audio tools to turn a script into an audio file. These recommendations emphasize the importance of the script.
For more detailed instructions, see Creating AI audio from a script. For help deciding when AI audio is appropriate, see When to use AI audio.
Writing scripts
Creating a high-quality script will ensure the best results with this tool. First, we’ll cover general audio recommendations. After that, you’ll find recommendations that are specific to the AI audio tool.
General recommendations
Write for the ear, not the page
- Be brief: Use relatively short sentences. Turn phrases in parentheses into separate sentences, because a listener can’t see the parentheses. Sentences that look too simple on the page sound clear when you read them aloud.
- Use informal language, including contractions (it's, you'll, they're, isn't). You can start a sentence with “And” or “But.”
- Read every script aloud to ensure that it fits the natural rhythm of a spoken voice.
Engage the listener
- Write as if you're speaking directly to one person: Use “you” and “we” to make the experience feel personal and inclusive.
- Use sensory detail to make the material feel real and vivid. Invite the listener to notice what they can feel, hear, or see.
- Ask reflective or rhetorical questions. For example, “What might it have felt like to stand here, centuries ago?” or “Can you imagine the noise?”
Structure each stop as a self-contained story
- Give the most important or immediate information first. Start with the things the listener can notice right now. Add more detail as the stop continues.
- Get the listener's attention. Think about why they might care about the material.
- Cover one or two points per stop. A point might highlight a particular feature, a technique, or a piece of historical context.
- Order your points the way you want listeners to look at the work, so each one flows into the next.
AI audio recommendations
Clean up the script before generating your audio
Remove any characters that aren't meant to be part of the audio, like notes and bullet points.
Use punctuation to shape pacing
Listen carefully to the full audio file, especially to the pace of the reading and the pronunciation of names. For most languages, you can use standard punctuation to add pauses that make the recording sound more natural.
- Commas (,) add the shortest pauses.
- Hyphens and dashes (—) add brief pauses.
- Periods (.) add full pauses, and a falling tone to indicate the end of a sentence.
- Ellipses (...) add the longest pauses.
Spell out numbers and symbols
- Use numerals for 1–999, then words for larger numbers (“one hundred and twenty-three thousand, four hundred and fifty-six,” “million”).
- Clarify currency, times, dates, symbols, and numerals (for example, “twenty dollars,” “9 a.m.,” “nineteen ninety-seven,” “Henry the Eighth,” “20 percent”).
- Instead of using “.com”, spell out URLs with “dot com.”
Phonetic spelling
- If the AI mispronounces a name, try spelling the name phonetically. For reference, see Carnegie Mellon’s phonetic spelling instructions.
- Watch out for homographs (words that are spelled the same but pronounced differently, like “read” or “tear”).
Audio length and other specifications
- We generally recommend keeping audio files under 2 minutes, or 250–300 words. Shorter audio is easier for visitors to follow, but the AI audio tool can generate files up to 5–6 minutes if your guide requires it.
- File naming: use consistent, descriptive names so files are easy to find and organize.
Other considerations
- Choose your voices based on what fits your organization and audio goals. We recommend limiting the number of voices across your guide to three. Visitors will enjoy the consistency and familiarity that comes with a predictable voice, or set of voices.
- Listen through to the entire clip before publishing it. Follow the guidance above to adjust your script, or find more detailed instructions in Creating AI audio from a script.
- Don't use the tool to deceive visitors. For example, don't claim that the audio is a recording of a particular person.
- Audio is best used as a tool to tell compelling stories about your organization. General overviews, visitor information, or other non-interpretive content may be better suited in text.
Disclosing AI to visitors
The integrity of your collection is our top priority, and we strongly recommend that you disclose any use of AI tools. When deciding where that disclosure appears in your guide, only you can know what’s best for your organization and your visitors. For this reason, Bloomberg Connects doesn't automatically disclose the use of these tools for you.
Our recommendation is that you include a disclosure in the Description field of the Audio form. For example, “[Writer name]’s script is read by an automated voice,” or “In this recording, our script is read by an AI voice.”
Other places to disclose the use of AI audio include:
- In the Description field of an exhibition or tour that features AI audio files.
- In the script for the audio file itself, at the beginning or the end.
- In the Credit field for the item that features an AI audio file.
We don't recommend putting your disclosure in your audio’s Transcript field, because this suggests that the transcript is AI-generated. We also don't recommend putting it in your organization description, because then visitors can't tell which content is AI-assisted.