Text to Speech
Convert text to natural speech with 30 Gemini voices, 40+ accents, and a 12-style Voice Direction picker
Turn written text into natural, expressive speech. Kolbo's Text-to-Speech features 30 Gemini voices, each available in dozens of language and accent variants, plus a Voice Direction picker that lets you direct the delivery like a producer.
Overview
Text-to-Speech generates studio-quality voiceovers from text. Use it for narration, explainers, ads, character dialogue, audiobooks, and any project that needs a human-sounding voice. You choose the voice, the accent, and the way the line is delivered.
Gemini Voices
30 expressive Gemini voices, each with 40+ language and accent variants, including English (US, UK, AU, IN), Spanish, French, Portuguese, Hebrew, Arabic, Hindi, Japanese, Korean, Mandarin, and 20 or more others. Pick a voice, then select the accent or language that fits your audience.
Voice Direction
The Voice Direction picker lets you direct the delivery instead of accepting a flat read. Choose from 12 curated styles:
- Whisper
- Dramatic newscast
- Calm narration
- Storyteller
- TV commercial
- Cheerful
- Soft and intimate
- Excited and energetic
- Sad and melancholic
- Serious and professional
- British accent
- Warm and conversational
Or write a Custom direction prompt (up to 500 characters) for free-form control over tone, pacing, and emotion.
The chosen style is shown on each generated audio card, so you can see exactly how a take was directed and reproduce it.
How It Works
- Open Text-to-Speech in Audio Tools
- Paste or type your script
- Select a Gemini voice and the accent or language variant
- Pick a Voice Direction style, or write a custom direction prompt
- Generate, preview, and regenerate until the delivery is right
- Download the audio for your project
Tips
- Match the voice to the content - a documentary narrator and a TV commercial read need different voices and directions
- Use Voice Direction for emotion - the same line lands very differently as Calm narration versus Excited and energetic
- Write a custom direction when the 12 presets do not capture the exact mood you want
- Pick the right accent variant so the voice fits the audience and region