Voice and music · by Google

Gemini Speech

Voice a two-person script, directing the tone in plain words.

text → speech · text, speech → profile
Way in
Official APISign up yourself, api key
To start
Free tierfree tier input+output on 3.8 Flash and Flash-Lite TTS (rate limited)
Runs
In the cloudAlso through Vertex AI, Replicate, OpenRouter
Checked
Nov 3, 2026Prices as of that day

What it can do 2

Generate controllable speech or 2-speaker dialogue from a prompt2 speakers per request; custom voices 200/projecttext → speechFlash: $0.50/1M text in, $9/1M audio out (~$0.00225/10 s) through 2026, doubling 2027-01-01; Flash-Lite $6/1M out
Design a voice from text or replicate a voice from a samplereplicated voicekeys expire in 7 days; stored voices 1 yr after last usetext, speech → profilebilled as TTS tokens

Does the same job

Prices and limits as of Nov 3, 2026, from Google’s own pages. They change; check before you rely on them.Not affiliated with Google. Not advice.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.