Gemini TTS API pricing: what an hour of Gemini speech costs
Google’s Gemini TTS models are billed by tokens, not characters, so the price of a minute is not obvious at first sight. This guide lists the prices from the Gemini API pricing page as of November 2026, converts them into the cost of an hour of audio and compares them with a plan billed by time.
Prices per million tokens
Gemini 3.8 Flash TTS costs $0.50 per million text tokens in and $9 per million audio tokens out until December 31, 2026, then $1 and $18 from January 1, 2027. Gemini 3.8 Flash-Lite TTS costs $0.50 and $6, then $1 and $12. The older models cost $1 and $20 for 3.1 Flash TTS Preview and 2.5 Pro Preview TTS, and $0.50 and $10 for 2.5 Flash Preview TTS. Batch requests cost half these prices.
What an hour costs
Google counts 25 audio tokens per second, so an hour of speech is 90,000 audio tokens. That makes an hour about $0.81 with 3.8 Flash TTS and $0.54 with Flash-Lite in 2026, and $1.62 and $1.08 from 2027, plus the text input, which adds little. The 216 hours that the $5 SuperClonica Starter plan voices at most in a month would cost about $175 with Flash TTS and $117 with Flash-Lite at 2026 prices.
The free tier
The Gemini API has a free tier for 3.8 Flash TTS, 3.8 Flash-Lite TTS, 3.1 Flash TTS and 2.5 Flash TTS, with rate limits, and trying speech in Google AI Studio is free. According to the pricing page, Google may use free-tier content to improve its products, but not paid-tier content. On Google Cloud, Gemini-TTS has no free usage.
The same hours on SuperClonica
The SuperClonica speech API bills by time, not characters: a plan gives minutes of audio in every 10-minute window. Used without a break, the $5 Starter plan voices up to 216 hours a month, the $10 plan up to 576, $20 up to 1,440 and $50 up to 4,680. A free key gives 3 minutes a day. Every catalog voice and your own trained voices work on any plan, and audio streams back from 300 ms in our measurements. Supertonic 3 speaks 31 languages; Chinese is not among them yet.
When Gemini is the better choice
Gemini TTS speaks many more languages, including Chinese, takes style directions in plain words and can voice two speakers in one request. For a few hours a month it is cheap, and the free tier may be enough. SuperClonica pays off when you voice many hours a month, want character voices from the catalog or voices trained from your own recordings, or need a fixed bill.
Try it in one request
Get a free key on the site and post text to https://superclonica.com/api/v1/speech with the header Authorization: Bearer and your key, and the body
{"text": "...", "voice": "F1", "language": "en"}Add "format": "mp3" for MP3, or "stream": true to play the audio as it arrives.