Describe the host you want: warmth, pace, register, the kind of person behind the microphone. Mato designs an original voice from that brief, and you can hear the results below.
Every clip on this page was designed from a written brief. No person was recorded or cloned. The faces are Mato talent, shown for illustration.
01Brief
02Descriptors
03Voice
From the brief
A daily-briefing news host in his 40s with a neutral American accent and crisp, precise diction, speaking to one listener through headphones rather than announcing to a room.A daily-briefing news host in his 40s with a neutral American accent and crisp, precise diction, speaking to one listener through headphones rather than announcing to a room.
From the brief
An early-30s sports co-host with a Midwestern accent, talking to one listener through headphones rather than performing for a crowd.
From the brief
A calm, measured professional-services narrator in his 50s with an RP-leaning British accent and a low, resonant register.
From the brief
A calm, measured professional-services narrator in his 50s with an RP-leaning British accent and a low, resonant register.
From the brief
A soft-spoken wellness and health host in her 40s with a neutral American accent.
From the brief
A soft-spoken wellness and health host in her 40s with a neutral American accent.
From the brief
A late-40s markets and economy host with a General American accent, speaking as if explaining something to a friend across a kitchen table late in the evening, not addressing an audience.
From the brief
A warm, late-40s male finance and markets host with a General American accent.
From the brief
An authoritative but warm news anchor in his 40s with a neutral American accent and crisp, precise diction.
From the brief
A curious technology host in his mid-30s with a light Californian accent, speaking directly to one listener through headphones rather than projecting to a room.
Calm
Unhurried
Low
Crisp
Host
Warm
Unhurried
Mid
Playful
Co-host
Measured
Deliberate
Low
Precise
Narrator
Measured
Deliberate
Low
Precise
Narrator
Soft
Unhurried
Warm
Reassuring
Host
Soft
Unhurried
Warm
Reassuring
Host
Intimate
Unhurried
Low
Dry humour
Host
Warm
Unhurried
Low
Dry humour
Host
Authoritative
Brisk
Mid
Crisp
Host
Warm
Unhurried
Mid
Conversational
Host
News host, calm take 2
Designed from the brief with Mato Voice. Press play to hear the published clip.
Sports co-host, relaxed take 2
Designed from the brief with Mato Voice. Press play to hear the published clip.
Legal narrator, measured take 2
Designed from the brief with Mato Voice. Press play to hear the published clip.
Legal narrator, measured take 3
Designed from the brief with Mato Voice. Press play to hear the published clip.
Wellness host, soft take 2
Designed from the brief with Mato Voice. Press play to hear the published clip.
Wellness host, soft take 3
Designed from the brief with Mato Voice. Press play to hear the published clip.
Finance host, intimate take 2
Designed from the brief with Mato Voice. Press play to hear the published clip.
Finance host, warm take 2
Designed from the brief with Mato Voice. Press play to hear the published clip.
News anchor, authoritative take 2
Designed from the brief with Mato Voice. Press play to hear the published clip.
Tech host, relaxed take 3
Designed from the brief with Mato Voice. Press play to hear the published clip.
0:05
The device replays published clips from the showcase. Nothing is generated live on this page.
Designed voices
Hear what a brief becomes
Ten original voices from the studio's second showcase round. Each one started as a paragraph, not a recording.
01
News host, calm take 2
Calm
Unhurried
Low
Crisp
Host
Brief: A daily-briefing news host in his 40s with a neutral American accent and crisp, precise diction, speaking to one listener through headphones rather than announcing to a room. His register is low and his pace is calm and measured, never rushed and never carrying breaking-news urgency, with small natural pauses that give each story room to breathe. His energy is medium-low and his authority is warm rather than projected, the tone of a trusted morning radio voice keeping someone calm company while they get ready for the day. Suited for a daily news-roundup podcast meant to feel unhurried and quietly authoritative, never urgent or shouted.
0:05
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
02
Sports co-host, relaxed take 2
Warm
Unhurried
Mid
Playful
Co-host
Brief: An early-30s sports co-host with a Midwestern accent, talking to one listener through headphones rather than performing for a crowd. His energy carries the easy banter of a sports conversation but stays at conversational volume, amused and warm rather than hyped or shouting. His register is medium, his pace is medium and relaxed, with small natural pauses for reaction and thought, unhurried even when the topic gets exciting. Suited for a laid-back weekly sports recap and banter show built for headphone listening, not a stadium broadcast or a hype reel.
0:04
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
03
Legal narrator, measured take 2
Measured
Deliberate
Low
Precise
Narrator
Brief: A calm, measured professional-services narrator in his 50s with an RP-leaning British accent and a low, resonant register. His pace is deliberate and precise, his delivery authoritative but never cold, well suited to a legal and management-consulting show that explains complex regulatory and strategy topics to senior decision-makers.
0:05
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
04
Legal narrator, measured take 3
Measured
Deliberate
Low
Precise
Narrator
Brief: A calm, measured professional-services narrator in his 50s with an RP-leaning British accent and a low, resonant register. His pace is deliberate and precise, his delivery authoritative but never cold, well suited to a legal and management-consulting show that explains complex regulatory and strategy topics to senior decision-makers.
0:05
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
05
Wellness host, soft take 2
Soft
Unhurried
Warm
Reassuring
Host
Brief: A soft-spoken wellness and health host in her 40s with a neutral American accent. Her pace is gentle and unhurried, her volume low and soothing, and her tone carries warmth and quiet reassurance rather than clinical detachment. Ideal for a mindfulness, sleep, and everyday-health podcast meant to feel calming at any time of day.
0:05
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
06
Wellness host, soft take 3
Soft
Unhurried
Warm
Reassuring
Host
Brief: A soft-spoken wellness and health host in her 40s with a neutral American accent. Her pace is gentle and unhurried, her volume low and soothing, and her tone carries warmth and quiet reassurance rather than clinical detachment. Ideal for a mindfulness, sleep, and everyday-health podcast meant to feel calming at any time of day.
0:06
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
07
Finance host, intimate take 2
Intimate
Unhurried
Low
Dry humour
Host
Brief: A late-40s markets and economy host with a General American accent, speaking as if explaining something to a friend across a kitchen table late in the evening, not addressing an audience. His register is low and intimate, his energy is warm and medium-low, and his humor is gentle and dry rather than performed for effect. His pace is slow and steady, unhurried, with small natural pauses that let a thought land before the next one starts. He never projects, never rushes, and never raises volume for emphasis. Suited for a calm weekly markets show meant to be heard through headphones by one listener at a time, not shouted at a crowd.
0:05
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
08
Finance host, warm take 2
Warm
Unhurried
Low
Dry humour
Host
Brief: A warm, late-40s male finance and markets host with a General American accent. He speaks unhurried and low-key, with a dry, understated sense of humor and a steady, reassuring baritone. Suited for a weekly markets-and-economy show aimed at engaged, non-expert listeners who want calm, trustworthy analysis without hype.
0:05
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
09
News anchor, authoritative take 2
Authoritative
Brisk
Mid
Crisp
Host
Brief: An authoritative but warm news anchor in his 40s with a neutral American accent and crisp, precise diction. His pace is brisk and controlled, his register mid-to-low, and his delivery projects credibility and calm command without sounding distant. Suited for a daily news-roundup show that needs to feel trustworthy and current.
0:05
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
10
Tech host, relaxed take 3
Warm
Unhurried
Mid
Conversational
Host
Brief: A curious technology host in his mid-30s with a light Californian accent, speaking directly to one listener through headphones rather than projecting to a room. His register sits in a relaxed middle range, his energy is warm and medium-low, and there is an easygoing, thoughtful smile audible in his voice even while he works through an idea out loud. His pace is moderate and unhurried, leaving room to think and small natural pauses between thoughts, never rushed and never raised in volume or announcer projection. Suited for an intimate weekly technology and product-culture show built around a relaxed one-on-one conversation rather than stage energy.
0:05
Machine-designed from a text brief with Mato Voice. Not a clone of a real person.
11
The next voice starts with your brief
Describe the host your show needs. In a guided session we design candidates from that brief and audition them with you on your own scripts.
Showcase picks from the second review round, chosen by the Mato team. Clips are short excerpts, levelled to about -16 LUFS, with no edits to timing. New picks replace these as the studio grows.
The faces are Mato talent, shown for illustration. Every voice here was designed from text and is not a recording or clone of the person pictured.
Pick descriptors and add notes. The composer names the published voice that shares the most of them and writes a brief you can copy into your demo request.
Optional. Add references, accent detail, phrases that matter and anything to avoid.
Closest designed voice
Pick a few descriptors and the closest published voice appears here.
Your brief stays on this page until you copy and share it.
Two ways in
Design one, or clone one with consent
Start from a description when the show needs its own voice. Start from a recording only when the speaker has agreed to be cloned.
01
Voice design
Describe it in plain language
Warmth, pace, register, the kind of person it should sound like. We design the voice from your brief and iterate with you on real script lines until the delivery lands.
Bring clean recordings of an approved speaker. We build the voice on Mato Voice and check it against your own scripts so the read holds over a full episode.
Both paths are guided by our team and evaluated against the scripts your show actually publishes. Cloning requires documented consent from the speaker.
How a session runs
Three steps, one working voice
A studio session is guided. You bring direction and scripts; we bring the designer and the ears.
01
You send the brief
Descriptors, reference material, and the scripts you actually publish. Consent documentation too, if we are cloning.
02
We run the studio with you
We review the direction, generate candidates from the brief, evaluate them on your real script lines and narrow the brief with you.
03
The voice goes into production
After approval, our team connects the chosen voice to your show's workflow, ready for the next episode.
Voice Studio, explained
A few things to know
No. Every voice on this page was generated from a written brief by Mato's voice designer. No recording of a person was used, and none of them imitates a specific individual.
Yes, with documented consent from the speaker. Cloning runs on Mato Voice with clean recordings you provide. The comparison on the Mato Voice page shows what a clone sounds like next to other systems.
No. The composer builds a brief and points at the closest published voice. Generation happens in a guided session with our team, where the brief is turned into candidates you can audition.
The designer produces several candidates from the same brief with different seeds. Where two reads were both worth hearing, both are published so you can hear how much a take can vary.
After you approve a take, our team assigns it to a host in your Mato workspace. From then on, scripts for that host are produced with the voice, the same way as any other Mato host.
No. A designed voice is original and not modelled on a real person. How it may be used, and whether it stays exclusive to your show, is agreed with our team as part of the session.
Next step
Bring a script and leave with a voice you can hear
Send a brief and a real script passage. We will plan a guided session, design candidates from the brief and audition them with you.
