Audio model · from 3 credits
Generate a voice-over with Gemini 3.8 Flash TTS
Gemini 3.8 Flash TTS is Google's voice-over model, released on September 23, 2026: thirty named voices, one hundred and thirty languages, and delivery directed in plain words right in the node, "whisper, slowly", "radio host tone", "calm British accent". The model genuinely follows it, pace and breath included. It holds long texts in one take without the timbre drifting from one sentence to the next, which makes it valuable for narration, tutorials and audiobooks. Billed by the length actually produced, it is one of the cheapest voices on the site.
A voice you direct in plain words
Gemini 3.8 Flash TTS, released on September 23, 2026, is Google's voice-over model: thirty named voices, one hundred and thirty languages, and a direction field where you write what you want to hear, "whisper, slowly", "radio host tone, enthusiastic", "British accent, calm and measured". The model follows the direction, pace and breath included: the same sentence lasts half again as long when you ask it to whisper.
It holds a long text in a single take without the timbre changing from one sentence to the next, which makes it a voice for narration, tutorials and audiobooks. Speed has no slider: you ask for it in the direction. Billing follows the length actually produced.
Gemini 3.8 Flash TTS next to its closest siblings
Figures pulled from the same registry as billing: when a price or a cap changes, this table changes with it.
| Gemini 3.8 Flash TTS | OpenAI TTS HD | ElevenLabs Turbo v2.5 | |
|---|---|---|---|
| Base price | 2 credits / minute | 5 credits / 1,000 characters | 7 credits / 1,000 characters |
| Voices | 30 | 6 | 21 |
| Max prompt | 5,000 characters | 4,096 characters | 5,000 characters |
How to use it on Imaginode
- 1Add a Voice-over node from the toolbar.
- 2Write or wire in the text to read, pick a voice: the price follows the text length.
- 3Generate, listen in the node and download the MP3.
Frequently asked questions
Which languages does Gemini 3.8 Flash TTS speak?
One hundred and thirty languages, detected from the text, including French, English, Spanish, German, Japanese and Arabic. A regional accent is requested in the direction field.
How much does a voice-over generated with Gemini 3.8 Flash TTS cost?
2 credits per minute of voice produced, about $0.02 (1 credit = $0.012). Billing follows the actual length, to the second: the amount reserved shows before generating and any excess is returned as soon as the file is ready.
Which voices does Gemini 3.8 Flash TTS offer?
30 to choose from, up to 5,000 characters per generation, and delivery directed in plain words (tone, pace, accent) that the model follows. The voice-over node produces a downloadable audio file, billed by the length produced.
Can I try Gemini 3.8 Flash TTS for free?
Yes: signing up grants trial credits, no credit card required. Enough to test Gemini 3.8 Flash TTS in real conditions before deciding on a plan or a top-up.
Do I need to install anything to use Gemini 3.8 Flash TTS?
No: Gemini 3.8 Flash TTS runs server-side, in the browser, mobile included. Imaginode's node canvas wires its renders to the other models (references, camera, styles) with nothing to install.
Gemini 3.8 Flash TTS at the competition
Gemini 3.8 Flash TTS or its variants are also available at ElevenLabs. Pricing grid recorded on a given date, sources cited: the comparison details what credit-based billing changes.
Read the Imaginode vs ElevenLabs comparison →
Try Gemini 3.8 Flash TTS on a real canvas
112 models, one account, credits that work everywhere. The price always shows before you generate.
Get started
ElevenLabs v3
MiniMax Speech 2.8 HD