THE SHIFT
From Content Creation to Real-Time Voice AI Experiences
The first wave of generative AI transformed content creation. Text, images, video, and speech can now be produced on demand, turning ideas into content with a prompt. Most of this content still takes the form of a finished artifact, created once and then consumed. The next wave brings interactivity, with real-time voice AI powering characters, games, companions, interactive stories, and voice agents that respond continuously to each user, context, and moment.
Content now responds continuously to the people experiencing it.
This paradigm shift expands what users expect from text to speech AI voices beyond naturalness. Natural-sounding speech remains the foundation of a high-quality voice experience, while interactive experiences introduce three additional requirements:
Diversity
Give every character a distinct voice.
Controllability
Adapt each performance as intent and context evolve.
Low Latency
Preserve the natural rhythm of interaction.
Together, these capabilities allow a voice to be designed for the character, directed for the moment, and delivered in real time.
THE NEW MODEL
Breeze TTS 2, a new speech model built for interactive experiences.
Breeze TTS 2 brings natural-language voice design, voice direction for any voice, and low-latency streaming generation together in a single model. Built for the next generation of real-time voice AI, it enables users to design any voice, direct every performance, and bring it to life in real time.
Advancing these capabilities also requires better ways to measure them. TTS evaluation has historically centered on naturalness, leaving voice design, voice direction, and latency less systematically explored. Breeze TTS 2 brings these capabilities together in a single model built for interactive voice experiences, giving creators and developers greater control over how voices are designed, performed, and delivered in real time. To support continued progress in these areas, we are also releasing open-source benchmarks for Voice Design, Voice Direction, and Latency. Now, let's take a closer look at the four capabilities that define Breeze TTS 2: voice design, voice direction, low latency, and multilingual speech.
CAPABILITY 01
Voice Design - the right AI voice for every character
Breeze TTS 2 gives every character a voice of their own, from a single protagonist to thousands of NPCs. Instead of relying only on preset voice libraries, creators can describe the character they have in mind and generate distinctive text to speech AI voices that better match each role, personality, and world.
Breeze TTS 2
MiMo-V2.5-TTS
Inworld Voice Design
Fun-AudioGen-VD
Eleven v3
Qwen3-TTS-VD
VoxCPM2Breeze TTS 2 ranks first on the TTS Voice Design Benchmark, achieving the highest Role Fit score (78.02) and greatest Voice Diversity (708), with a 98.5% Transcript Pass rate. It leads the next-best model by 5.24 points in Role Fit and produces 39% more distinct voices than the closest competitor.
Animation & Comics
PROMPT
Masculine, mature adult. Massive heavy-set alien. Deep, gravelly, resonant bass-baritone. Gruff, authoritative, commanding, drill-sergeant cadence. Fast, high-intensity. Rough, weathered, immense power, stern mentorship.
SCRIPT
Chest up, eyes forward. Space does not care if you're tired, scared, or homesick; it only rewards discipline. Stay on my count, recruit, and I'll drag a champion out of you yet.
Film & TV
PROMPT
Young adult female, mid-20s, American accent. Professional broadcast journalist turning frantic. Clear, articulate but strained by panic. High tension, rapid pace, breathless. Polished to raw desperation.
SCRIPT
This is Elena Vance, reporting live from the east block where the crowd just broke the barricade—if anyone can hear me, we need medical teams now, please, they're getting closer.
Games
PROMPT
Female, young adult, ethereal trickster. High-pitched, breathy, mischievous. Fast, rhythmic delivery with giggles. Mocking sing-song riddles. Playful, taunting, otherworldly.
SCRIPT
Oh, you heard the whisper too? Clever little heartbeat. Follow the violet shimmer if you dare, but mind your shadow, love. It tends to trade secrets when the veil grows thin.
Literature & Stage
PROMPT
Male, mid-20s to early 30s. Smooth velvety tenor-range speaking voice with a light rasp. Soulful and deeply emotive, shifting from weary struggle to optimistic conviction. Impeccable diction, gentle Southern lilt, deliberate pace, and broad expressive pitch arcs.
SCRIPT
I've walked through too many long nights to mistake silence for peace, so when I speak of tomorrow, believe me, brother, I mean a dawn we can finally stand in together.
Myth & Folklore
PROMPT
Mature nomadic storyteller. Weathered, resonant speaking voice with rhythmic pacing and expressive pitch contours. Wide dynamic range from hushed whispers to booming proclamations; soulful.
SCRIPT
Come closer to the fire, child; the wind is telling old truths tonight. Hear how it bends the grass, then remember this: every road you take is also taking measure of you.
Research & News
PROMPT
Mature male, 50s-60s, Japanese-accented English. Dignified, measured, stoic tone. Clear texture with slight age rasp. Deliberate pacing, significant pauses. Conveys wisdom, authority, and visionary caution.
SCRIPT
We do not rebuild a nation with noise or haste. We place each stone with care, and when doubt rises, we answer it with discipline, patience, and an unshaken sense of duty.
Web & Periodical
PROMPT
Ancient male, massive scale. Deep, resonant bass, gravelly, subterranean. Slow, deliberate, aristocratic. Terrifying power, sibilant, predatory intelligence.
SCRIPT
Careful where you place your little hands, treasure-seeker; every coin in this vault knows its master, and I am not inclined to forgive even the smallest theft.
CAPABILITY 02
Voice Direction - the right performance for every moment
Use natural-language instructions and inline tags to shape emotion, intent, pace, and delivery while keeping every character recognizable. This gives creators and developers greater control over how an AI voice performs from one moment to the next without having to redesign the voice itself.
Breeze TTS 2
MiMo-v2.5-TTS
StepAudio 2.5 TTS
Qwen-Audio 3.0-TTS-Plus
Inworld TTS-2
VoxCPM2Breeze TTS 2 achieves the highest Voice Direction Score (4.25), outperforming the next-best model by 13%. Combined with a SIM score of 0.67, the result demonstrates its ability to follow natural-language direction across emotion, intent, pace, and delivery while keeping the selected voice recognizable across different performances.
Communicative Intent
PROMPT
Speak with an alluring, hushed intensity, using a hypnotic and persuasive rhythm to draw the listener in and convince them to acquire a rare item.
SCRIPT
You feel the energy radiating from it, don't you? This isn't just a piece of quartz. It's a conduit. For a small offering, you can take it home and finally clear that dark cloud hanging over your future. Trust me, you need this.
REFERENCE
OUTPUT
Composition
PROMPT
Speaking while heavily out of breath and gasping for air, trying to reassure the listener that everything is fine.
SCRIPT
[gasps] I'm okay... [pants] just give me a second to catch my breath. [gasps] I promise, I'm completely fine... just ran a little too fast.
REFERENCE
OUTPUT
Emotion
PROMPT
The speaker sounds acerbic and bitter, delivering the lines with heavy, passive-aggressive sarcasm.
SCRIPT
Enjoy your vacation while I stay here and clean up the mess you left behind for me. Have a wonderful time.
REFERENCE
OUTPUT
Role
PROMPT
Speak with a gritty, swaggering, and theatrical tone, projecting an aggressive and boastful attitude of a seafaring marauder.
SCRIPT
Drop the anchor and bring out the gold! If any of you scallywags think about crossing me, you'll be swimming with the sharks before sunset. This ocean belongs to me!
REFERENCE
OUTPUT
Variation
PROMPT
Start with a confident, reassuring tone. At the word 'Wait', suddenly shift to terrified, breathless alarm as if reacting to a frightening noise.
SCRIPT
There's absolutely nothing to worry about, I've done this a hundred times before. Wait... did you hear that sound? Something's definitely not right here.
REFERENCE
OUTPUT
CAPABILITY 03
Low Latency - Real-Time Voice AI at the Speed of Conversation
Breeze TTS 2 brings naturalness, voice design, and voice direction into a single low-latency model built for real-time voice AI applications. Fast time to first audio helps conversations stay responsive and preserves the natural rhythm of interactive voice experiences.
Breeze TTS 2 ranks first on the TTS Latency Benchmark, delivering the fastest time to first audio at both p50 and p95. Its consistently low latency keeps realtime interactions responsive and preserves the natural rhythm of conversation.
Streaming Breeze TTS 2 in realtime
The realtime API keeps one WebSocket session open across conversation turns: append text as it arrives, and raw PCM audio streams back while the model is still generating.
import { BreezeBlueClient } from "@breeze.blue/sdk";
const client = new BreezeBlueClient();
// One WebSocket session, many conversation turns.
const connection = await client.textToSpeech.realtime.connect("voc_...", {
modelId: "breeze-tts-2",
});
const consumer = (async () => {
for await (const message of connection) {
if (message.type === "audio") {
play(message.audio); // raw PCM, streamed while the model generates
} else if (message.type === "turn.done") {
return;
}
}
})();
connection.startTurn("turn_1");
connection.appendText("Hello from Breeze TTS 2.");
connection.flush();
connection.endTurn();
await consumer;
connection.close();CAPABILITY 04
Multilingual Speech
Create natural, expressive text to speech AI voices across 50 languages, with accent control for adapting delivery to different regions and audiences.
Choose a language
Every journey finds its meaning when someone dares to take the first step.
Original: Every journey finds its meaning when someone dares to take the first step.
