PeachDesk Voice Studio turns text into natural-sounding speech directly from your browser. All synthesis runs on BibhaтАЩs hosted GPU infrastructure, so thereтАЩs nothing to install and no models to download. Open Voice Studio from your PeachDesk dashboard and head to the Generation tab to get started.

тАЛ
Basic Generation

1

Open the Generation tab

From the PeachDesk dashboard, launch Voice Studio and select the Generation tab.
2

Select a voice

Pick a voice profile from the dropdown. You can use a Built-in voice or a profile youтАЩve created with Clone from audio in the Voices tab.
3

Choose a model

Select a synthesis model/engine from the dropdown. Models are hosted and served by PeachDesk тАФ no download or setup required.
4

Enter text

Type or paste the text you want to synthesize into the input box.
5

Generate

Click Generate and wait a few seconds while the request is processed on PeachDeskтАЩs servers.
6

Play & export

Preview the result in the player, then download it or save it for use in your Stories and Captures.

тАЛ
Text Formatting Tips

The way you format text affects the quality and naturalness of the output.

тАЛ
Punctuation

Use proper punctuation for natural pauses and intonation:

тАЛ
Emphasis

Use formatting to suggest emphasis:
The model interprets these hints, but results may vary between voices and models.

тАЛ
Advanced Features

тАЛ
Working with Long-Form Content

For long-form content, split your text into smaller chunks. Shorter segments give you finer control over each take, generate faster, and make it easier to regenerate only the parts you want to change. Each generated segment becomes a take you can review and refine.

тАЛ
Faster Re-Generation

Voice Studio caches voice prompts on PeachDeskтАЩs infrastructure, so re-generating with the same voice profile is faster after the first run.

тАЛ
Applying Effects

Once youтАЩve generated speech, switch to the Effects tab to apply adjustments. Effects are applied as versioned takes, so you can compare results and roll back to an earlier version at any time.

тАЛ
Coming Soon

  • Real-time streaming
  • Word-level timing control
  • Emotion and style controls
  • SSML support
Looking for more? Explore the Stories, Talk, and Captures tabs to build longer projects and conversational audio from your generated speech. Full documentation is available at docs.peachdeskai.com.