Voice Personalities

​

Overview

A personality is an optional free-form description attached to a voice profile — who this voice is, how they speak, what they care about. Set one and two new controls appear next to the generate button on the Generation tab, both powered by an LLM that PeachDesk Voice Studio runs for you on its GPU servers:

• Compose — drop a fresh in-character line into the text box. Click again for a different take.
• Speak in character — a toggle that rewrites your input text in the character’s voice before TTS, preserving every idea.

The LLM produces the text. The voice profile speaks it. You never download or manage a model — Voice Studio hosts the LLM and the TTS engines together, so the whole loop happens on our servers and streams the result back to your browser.

​

Setting a personality

Open a voice profile in the Voices tab and switch to its edit view. The Personality field is free-form text up to 2,000 characters. Describe the voice however helps you — past lines they’d say, speech patterns, tone, boundaries. Good descriptions tend to include:

• A one-line identity (who they are)
• Speech patterns (rhythm, vocabulary, what they avoid)
• Representative phrases — example lines show the LLM the target tone better than adjectives
• What the character wouldn’t do (they don’t explain, they don’t apologize, they refuse to break character, etc.)

You can set a personality on any voice profile, whether it’s a Clone from audio profile or a Built-in voice. The actions work identically regardless of which engine the profile uses.

​

The two actions

Each action is tuned for a specific job, and the LLM temperature is adjusted to match.

​

Compose

Generate a fresh utterance in the character’s voice, with no seed text. Click the shuffle button to drop a line straight into the generate text box; click again for a different take.

• When to use: prototyping, sampling a character’s voice, brainstorming a line without typing one first
• Temperature: hot — variety is the point
• Typical output: a short, punchy line that fits the character’s register

​

Speak in character (rewrite)

Flip the persona toggle and whatever you type (or dictate) gets rewritten in the character’s voice before TTS — every idea preserved, only the phrasing changes. This is the high-fidelity mode: the content doesn’t change, only the voice does.

• When to use: turning a dictated memo into in-character speech; lifting a plain-English script into a specific voice without editing by hand
• Temperature: cold — faithfulness wins
• Typical output: same ideas, same order, different phrasing and cadence

​

Speech-only framing

Both actions enforce speech-only output. The LLM is prompted to produce things a person would actually say out loud — no narration, no action tags (*sighs*, [laughs]), no meta-commentary, no markdown formatting, no stage directions. This is deliberate: the output goes straight into TTS, and anything that isn’t speakable ends up either ignored or read literally. The speech-only framing also makes the output land cleanly inside dialogue, so you can drop a result straight into a Story.

​

The hosted LLM

PeachDesk Voice Studio serves the personality LLM for you: BRAHMA-30B, Bibha’s self-hosted language model, running on our GPU infrastructure. You don’t download anything, and there is no size to pick — the model is pinned server-side, so it shows read-only in Settings → Captures → Refinement → Refinement model. The same model backs transcript refinement, so a personality rewrite and a cleaned-up dictation transcript come from exactly the same place.

​

Using the controls

Both controls appear next to the generate box on the Generation tab when the selected profile has a personality set. Compose always gives you something different on re-click. The persona toggle, on the other hand, is a mode — it applies to every generate call until you flip it back off.

​

Use cases

• Agents that speak in a voice you own. Connect a PeachDesk agent to a profile with a personality and have it talk back in character — the agent asks Voice Studio to speak, and the text is rewritten in character before it’s spoken.
• Interactive characters. Games, narrative tools, accessibility experiences. A character with a personality description plus a cloned voice becomes a reusable prop.
• Accessibility. People who can’t speak in their original voice can keep a personality description of how they used to sound and use the rewrite toggle to turn typed input into in-character speech.
• Creative drafting. Write a plain outline, flip the persona toggle, generate line-by-line into the character’s voice, then drop the audio into a Story.

​

API surface

Personalities are also accessible from the PeachDesk API: POST /generate with personality: true is the same primitive the toggle uses in the UI, so scripts and connected agents can drive in-character speech directly.

​

Limits and gotchas

• The personality is a prompt, not a fine-tune. The LLM will sometimes drift out of character, especially on Compose at high temperature. Click again for another take.
• Long personalities are not always better. 2,000 chars is a ceiling, not a goal. A sharp 300-char description with two example lines typically outperforms a long one.
• Speech-only framing is enforced, but not bulletproof. Very large prompts or unusual inputs can sneak an action tag through. If you see [laughs] in TTS output, it’s usually a personality-field hint the model anchored onto — remove it from the description.
• Rewrite preserves meaning by design. If the output is changing your meaning, you probably want a fresh Compose with your context in the input, not the rewrite toggle.

​

Next steps