grok-tts

Available Models

grok-tts
$$$$
$15/1M

Provider Overview

Grok TTS is an expressive, human-like text-to-speech. It features five built-in voices and supports over 20 languages with automatic detection. Users and developers can also add inline tags to inject specific emotions like laughing, whispering, or natural pauses into the narration

Highly ExpressiveMultilingualSpeech tags support
26Total Voices
19Male
7Female

Vocal Signature

Distribution of tonal characteristics (1-10)

Detailed Metrics

🎭

Expressiveness

Mostly Standard. Polite, conversational, and professional. Typical for assistants and news.

🌵

Roughness

Mostly Silky. Synthetic perfection or high-end commercial polish. No audible grit.

📢

Projection

Mostly Conversational. Speaking naturally to a person 3 feet away.

⏱️

Tempo

Mostly Flowing. Natural conversation or deliberate explanation.

☀️

Brightness

Mostly Neutral. Natural balance between highs and lows.

〰️

Instability

Mostly Stable. Confident, solid breath support, and unwavering pitch.

🗣️

Articulation

Mostly Professional. Broadcaster crispness with clear T's and K's.

👤

Perceived Age

Mostly Adult/Mature. Established adult, approx. 35-55 years old.

Popular Voices

Casting Studio Chat
Hi! I am your Acoustic Casting Assistant. I can help you find the right voice based on the vibe you need, or give feedback on any voice you are listening to.

Guest Session: History not saved

Describe the voice you need... Use '@' for specific voices, or '/' to filter by provider.