Whether you're producing training content, marketing audio, or anything in between, Studio gives you everything you need to go from script to finished audio. This guide covers each step of that process.

Before you start

You will need:

• A WellSaid account. Sign up for a Free Trial at wellsaidlabs.com if you don't have one.
• Your script. Have your text ready to enter or import.

Create a new project

1. Log in to your Studio account.
2. Select Projects from the left menu.
3. Click + New in the top-right corner.
4. Enter a name under Project details.
5. Click Create project.

Choose a voice

1. Open the voice selector using one of these options:
   • For a quick pick, click the voice selector in the section header.
   • For the full library, select See all voices from the right sidebar.
2. Browse voice options and listen to samples.
3. Use the Style dropdown to explore variations.
4. Select a voice to apply it to your active section. You can change it later if needed.

Select a model or language

1. Open the section Style dropdown.
2. Choose the model you want to use.

Enter and structure your script

1. Paste, type, or click Import Script to add your content.
2. Organize your script using one of these options:
   • For one section per paragraph, choose Split by paragraph.
   • For individual sections per sentence, choose Split by sentence.
   • For full control over section structure, choose Manual.

Generate your first take

1. Click the Play button to generate audio for the active section.
2. Review the take and adjust the script if needed.
3. Click Play again to generate new takes to compare.

Manage your takes

Sections support multiple takes, giving you flexibility as you refine.

• Regenerate a take: Click the Regenerate icon (circling arrows) to create a new take.
• View take history: Click Take [#] at the top of the section or open Take History in the right sidebar.
• Repopulate a take: Open Take History, then select Use this take to restore both the audio and related text.
• Delete a take: Use the ellipsis (…) menu next to a take to delete it.
• Download a take: Click the Download icon and choose your file format (MP3, WAV, or OGG).

Fine-tune your audio

Use the features below to help you improve clarity, pacing, emphasis, and overall performance.

Pronunciation tools

• Respelling suggestions (Oxford & Smart Suggestions)
  • Double-click or highlight a word to pull up the Smart Toolbar and view suggestions. Apply them to fix mispronunciations while keeping your script intact.
    • Oxford Suggestions: Provides accurate respellings for over 250,000 British and American English words.
    • Smart Suggestions: AI-generated respellings for words not covered by Oxford, such as proper names, acronyms, or brand-specific terms.
• Create a phonetic respelling
  • Create your own respelling by breaking a word into syllables and indicating how it should sound.
  • Best for specialized terms or cases where suggestions don't match your desired pronunciation.
• Replacements
  • Use a replacement to substitute a word, term, or phrase with an alternative spelling when the pronunciation is otherwise ambiguous.
  • Example: Change "1099-MISC" from "ten ninety-nine M I S C" to "ten ninety-nine miscellaneous."
  • Store replacements in your Replacement Library to ensure the same word is read consistently every time.
• Acronyms
  • Some acronyms sound like words (NASA); others are spelled out (NBA).
  • Use respellings or replacements when Studio misinterprets them.
  • This helps voices distinguish pronunciation types.
• Numbers
  • Numbers can be read as dates, values, quantities, or references.
  • Add context or replacements to guide the correct reading.
  • Especially useful for addresses, IDs, and dates.

Script shaping tools

• Voice Cues
  • Use Voice Cues to shape delivery without rewriting your script. You can adjust:
    • For louder or quieter delivery, adjust Loudness.
    • For faster or slower delivery, adjust Pace.
    • For higher or lower tone, adjust Pitch.
    • For intentional breaks at commas or periods, adjust Pause.
  • Highlight text to reveal available cues in the sidebar, then apply and preview your changes.
  • Or use an Emotional Preset as a starting point.

• Add emphasis
  • Place a word or phrase in quotation marks (" ") to signal emphasis.
  • This helps voices stress key points.
• Pauses (commas, periods, ellipses)
  • Punctuation directly affects pacing:
    • Commas (,) create a light, natural pause.
    • Periods (.) create a stronger pause with a downward inflection.
    • Ellipses (...) create a longer, more conversational pause.
  • For longer breaks, use Pause Cues or set pause durations when combining sections.
• Shaping questions
  • Some questions need guidance to achieve a natural upward inflection.
  • Use punctuation (commas, ellipses) or rephrase slightly to help the model deliver the intended tone.

Organize your sections

• Rename a section: Click the section title, enter the new name, and click outside to save.
• Rearrange sections: Drag and drop sections into the order you want.
• Combine sections: Before you begin, ensure your sections have been rendered.
  1. Select multiple sections or click Select all at the top of the section list.
  2. Click Download, then select Download audio as: Combined file.
  3. Choose a pause length: Small (0.3 seconds), Natural (0.8 seconds), Long (1.2 seconds), or a Custom value up to 10 seconds.
  4. Name your file. The file name is used for the downloaded audio.
  5. Optional: Enable captions (SRT/VTT).

Download your audio

• Download individual takes directly from each section.
• Combine and download audio from multiple sections as a single file.
• Include optional caption files (SRT/VTT) when combining sections.

You now have everything you need to go from a blank page to finished, professional audio in Studio.

FAQs

Q: Can I change the voice after I've started writing my script?
A: Yes. You can change the voice on any section at any time. Generating a new take with the updated voice will reflect the change.

Q: What's the difference between a section and a take?
A: A section holds a portion of your script. A take is a generated audio rendering of that section. Each section can have multiple takes so you can compare and choose the best result.

Q: Do Voice Cues work with all voices?
A: No. Voice Cues availability depends on the selected voice and model. Check the sidebar after selecting a voice to see which cues are supported.

Q: Can I reuse the same audio project for a different script?
A: Projects are tied to their sections and takes. For a new script, create a new project to keep your work organized.