Configure voice and delivery

Every talent in Mato carries its own voice configuration. The settings you choose here control how the talent sounds during episode audio rendering, and they apply to every podcast the talent is assigned to (unless overridden at the podcast level).

Open the voice card

Go to Talent in the sidebar, then click the talent you want to configure. The Voice card sits near the top of the talent page.

The card shows the current voice (for example Preset voice: Liv, a Gemini preset), a set of Audition clips, and the Delivery settings: Accent, Speech speed, Speaking style, Audio profile, and Director notes. As the card puts it, who the talent is stays the same if you swap the voice.

To change the voice, click Change voice, either on the card or next to Edit profile in the page header, or click Manage next to the current voice. This opens Voice studio for that talent (for example Give Elena Reyes a voice), where you can pick a preset, clone a real voice, or design one from scratch. See Give a host a voice for each route. Voice changes are saved separately from the personality profile.

Choose a voice

Mato supports two voice providers. The one you pick determines which voice library appears.

Gemini voices

In Voice studio, click Pick a preset to see the preset voices. Each entry shows the voice name and a short description, such as "Female, warm and conversational voice. Great for engaging storytelling." Click a voice to select it, then click Use this preset.

Click the play button next to any voice to hear a short preview before committing. The preview may take a second to load.

Mato includes 29 preset voices (14 female, 15 male), each with a display name and a short description of how it sounds. A preset replaces any designed or cloned voice the talent had.

ElevenLabs voices (admin only)

The ElevenLabs voice selector appears only for super admins. It pulls voices from your connected ElevenLabs account. If you see only the Gemini selector, your account does not have ElevenLabs access enabled.

The card tracks which provider you last selected and saves that choice with the rest of the talent's voice settings.

Delivery settings

Accent, speech speed, speaking style, audio profile and director notes are shown under Delivery on the Voice card. Voice studio does not include them.

Set the accent

The Accent field sets the English accent the voice uses, for example General American.

Adjust speech speed

The Speech speed control sets pacing during audio rendering. Four presets are available:

• Slow sets a deliberate, measured pace with extra time between phrases.
• Normal keeps the default conversational tempo.
• Fast adds forward momentum with brisk delivery.
• Very fast creates rapid, high-energy output with minimal pauses.

Speed presets inject pacing directives into the TTS prompt that override other pacing guidance, so what you select here always takes priority.

Write an audio profile

The Audio profile is a free-text field where you describe how the talent should sound in the final mix. Think of it as a note to the audio engine about the talent's overall sonic character.

Example: "Warm and intimate, as if speaking to a friend across a coffee table. Slight vocal fry on lower register."

Add director notes

Director notes guide tone, pacing, and delivery in more specific terms than the audio profile. These notes are included in the TTS prompt that controls how the voice renders each line.

Example: "Lead with curiosity, not authority. Pause briefly before key statistics. Avoid sounding rushed during transitions between segments."

Director notes and speech speed work together. If your notes mention pacing and you also set a speed preset, the speed preset takes priority for tempo, while the director notes still influence other aspects of delivery like emotion and emphasis.

Save your changes

In Voice studio, apply a preset with Use this preset and a cloned voice with Save cloned voice. Click Done in the top-right corner to go back to the talent page.

Talent also needs a saved voice before it can be assigned to a podcast. If you try to add an unvoiced talent from a podcast's Hosts section, Mato shows a warning and keeps the assign action disabled.

Preview with audio samples

Audio samples let you hear how a talent sounds before using it in a real episode. They appear under Audition on the Voice card.

The Audition section lists the clips (such as News Intro, Casual Conversation, and Storytelling) with a play button and duration, so you can listen without leaving the talent page. The redesigned edit page no longer has an audio samples section.

Per-podcast talent settings

When you assign a talent to a podcast, the podcast uses the talent's default voice settings. You can review the current assignment from the podcast settings page.

Open your podcast and click Hosts & voices under Configure in the show's sidebar. The Hosts card lists each assigned talent with a role badge (Host · speaks first for the lead, Co-host for the second), then their type and pace, for example "Fictional · rapid pace". The voice is set on the talent, not here.

The pace on each row reflects the talent's speech speed: measured for Slow, natural for Normal, brisk for Fast, and rapid for Very Fast.

Open a row's ··· menu and choose Open talent to go to the talent profile and edit the talent's base voice settings. A voice belongs to the talent, not the show, so every episode from then on uses the new voice.

Quick reference