Landmark DocsDashboard →

On stream

Text to speech

Landmark reads messages out loud on your stream. A new account starts with it on and free: every chat message on every platform you connect is read in Matthew once the dock or the overlay is playing, and viewers may pick a free voice. Accounts that already set it up keep their settings.

Reads aloud

Three switches decide what gets read. Each has its own voice.

Chat messages
Every chat message, on every platform you connect, in the voice you pick. Matthew reads until you pick another. You can limit it to followers, subs, or mods.
Read my message
A Skill you price in the dashboard. Viewers redeem it with coins on your portal, or with bits, channel points, a gift or a tip on the platforms you set, and their words are read in the voice you pick for it. Prices and platform rules live on the card, like every other Skill.
Subs, gifts and raids
Says a short line for each with the viewer's name. You can change the lines. A Kick or TikTok item gift is announced by the gift's own name.

Turn a switch on and pick its voice. One master switch at the top turns everything off without losing your settings.

On your portal

Skills you make in the dashboard show to viewers on your portal. Read my message is a Skill under the Voice heading while you are live. When the tip rule is on, the Voice heading also has Read aloud, and Say it sits with the quick skills under the player. Both send a tip with a message, and the message is read. They only show while reads can be heard on your stream.

Plays in

My Control Dock: open the dock and it reads aloud. Nothing to add to OBS. Or My OBS overlay: add the Speech element to your overlay and the reads play there. Reads wait in one line and play one after another. Chat only joins the line while the dock or overlay is open, so nothing piles up while you are away.

Filters

Four word groups you can turn on: slurs, sexual, swears, violence. Slurs are on for everyone. Type a message into the Try it box and it shows you exactly what would be read, or why it would be blocked. Under More filters: swap one word for another, remove links, calm down shouting, block a viewer, and the pacing between reads.

Ordinary words that only contain a blocked word, such as tycoon or grape, still read. Short blocked words that hide inside other words block only as whole words.

Viewers pick a voice

Under Pick their own voice you choose Anyone, Subs only or Off. A new account starts on Anyone. Viewers can only pick free voices, so a viewer can never run up your bill. Brian starts switched off for viewers. Turn it on for them on the Voices page.

!setvoice <voice>
Pins that voice for the viewer's own messages. !myvoice works the same.
!clearvoice
Clears the pinned voice. The viewer goes back to your voice.
!voices
Lists the voices viewers can pin.

Viewer voices

A viewer can save their own voice once, from My voices in their dashboard. It belongs to them, works on every stream, and stays saved. Saving costs 300 coins for an instant voice, or 3,500 coins for a professional voice made from at least 30 minutes of recordings. Reading their own chat messages in their voice bills per character, charged to the letter, so a short message costs a fraction of a coin.

A viewer can give a voice to you in two taps. It shows in your voice list under From viewers, and you can use it for any read like another AI voice. When it reads on your stream it bills your usage per character, like your other AI voices. The viewer never pays for your use, and they can take the voice back at any time. A voice that is taken back stops reading and the rule that used it falls back to the free voice.

What it costs

Voices differ in cost, and the settings page tells you which is which.

Free voices
Matthew, Brian and about a dozen classic voices. Free up to 1,000,000 characters a month, then $0.0044 per 1,000 characters.
AI voices
Lifelike voices. They bill per character on every read. An AI voice is marked AI wherever you pick one.
Novelty voices
Animalese, Sans, Blip, Morse. Made in your browser. Never bill.

The Usage pill at the top of the settings page shows what this billing period cost so far. Only what is actually read bills. A blocked or skipped message bills nothing. The full rates are on the fees page.

Hear the voices

Each clip says the same line so you can compare. Press play.

Animalese
0:00 / 0:00
welcome to the stream
Chirpy, one chime per letter. Free, made in the browser.
Sans
0:00 / 0:00
welcome to the stream
One deep blip per syllable. Free, made in the browser.
Tomodachi
0:00 / 0:00
welcome to the stream
A Mii-style sing-song voice. Gold only. Bills per read.
DECtalk
0:00 / 0:00
this is the dectalk robot voice
The classic 1980s robot voice. Bills per read.

Every voice is on the Voices page with a play button.

Advanced

Advanced rules

Under the settings there is an Advanced rules list. Every read follows it, top to bottom, and the first rule that matches wins. The three switches set these rules for you. Open the list only when you want something specific: a paid read with a price per message, a rule for one platform, a rule for one person, or a different voice for cheers than for tips. Reset to the switches rebuilds the list from the switches if it ever gets tangled.

The tip rule reads paid messages from every platform: Landmark tips, Rumble Rants, YouTube Super Chats, a cheer of 100 bits or more with a message, and a Kick gift of 100 Kicks or more with a message. When Read my message is switched on, the tip, bits and channel point rules go quiet, so nothing is read twice.

Voice commands in chat

Tomodachi and Animalese read a short command at the start of a message and change how they sound. Put it in square brackets, then a space, then the message. The command is not read out.

High and fast
[p85,s70] hello chat, i am wide awake
Low and slow
[p15,s30] greetings... from the deep
Tomodachi preset
[v3] try voice three through [v8], and [v5,p80] for a preset plus a tweak

p is pitch and s is speed, 0 to 100. Tomodachi also reads q quality, t tone, a accent and i intonation.

[p85,s60] welcome to the stream
0:00 / 0:00
welcome to the stream
High pitch, a bit faster.
[p20,t30] welcome to the stream
0:00 / 0:00
welcome to the stream
Low pitch, dark tone.

Make Tomodachi sing

Start the message with [sing], then write each word with the note it lands on. A note is a letter A to G, an optional #, and an octave, like C4. Add :2 to hold a note.

[sing bpm150] ma{E4} ry{D4} had{C4} a{D4} lit{E4} tle{E4} lamb{E4:2}
Tomodachi singing
0:00 / 0:00
The notes above: "Mary had a little lamb". bpm sets the speed.

Elements can speak

Any element you build can call landmark.tts(text) to say something out loud, like when a goal is hit. It bills like any other read. See the element API.

Open Text to speech

Last updated · October 31, 2026

Text-to-speech · Landmark