Sign up and save up to 50% on a yearly plan.Sign up free →Black Friday: up to 50% off yearly plans.See the deal →

Steer the voice with a tag.

Gemini 3.1 Flash TTS AI voice generator

Google's Gemini 3.1 Flash TTS reads your script in one of 30 voices and 70+ languages. Audio tags like [whispering], [laughing] and [long pause] direct the read, at a low price per character.

From $0.031 per 1,000 characters on MAX yearly

  • 70+ languages
  • 30 voices
  • Up to 5,000 characters a read

● Made with Gemini 3.1 Flash TTS

Hear Gemini 3.1 Flash TTS

Every sample is one read, with the script that made it and what it cost.

  • “Welcome back to the channel. Today we are testing three budget microphones under fifty dollars, and the winner surprised all of us.”

    Kore
    131 characters · 1 credits
  • “[whispering] The library was silent. [short pause] Then somewhere in the back, a book fell. [shouting] Who is there? [long pause] [laughing] Oh. It was only the cat.”

    Leda · audio tags
    165 characters · 2 credits
  • “Pizza night just got easier. Order before six, and the second large pizza is half price. Tap the link and pick your toppings.”

    Puck
    125 characters · 1 credits
  • “The quarterly numbers are in. Revenue grew twelve percent, churn fell for the third quarter in a row, and the team doubled in size.”

    Charon
    131 characters · 1 credits

● Why people pick it

What is Gemini 3.1 Flash TTS good at?

01

200+ audio tags

Google says the model takes more than 200 tags: pacing, emotion and pauses, written in square brackets.

02

30 voices

Puck, Kore, Charon, Leda and 26 more prebuilt voices to pick from, one per read.

03

70+ languages

Localised, expressive speech for audiences around the world.

04

Low cost

One of the cheapest voices per character on OpenClips.

● Use cases

What people make with Gemini 3.1 Flash TTS

Stories and audiobooks

Google names audiobooks, storytelling and newscasts among the reads the model is built for.

Audio descriptions

Accessible narration for video, with pauses where the picture needs them.

Game and character voices

Expressive characters for games and immersive audio, steered with tags.

● Side by side

How does Gemini 3.1 Flash TTS compare?

The other voice models on OpenClips, on the same credits.

SpecGemini 3.1 Flash TTSElevenLabs v4 TurboDeepgram Aura-2MiniMax Speech 2.8 Turbo
Made byGemini 3.1 Flash TTSGoogleElevenLabs v4 TurboElevenLabsDeepgram Aura-2DeepgramMiniMax Speech 2.8 TurboMiniMax
Price per 1,000 charactersGemini 3.1 Flash TTS7.5 creditsElevenLabs v4 Turbo8.2 creditsDeepgram Aura-26.2 creditsMiniMax Speech 2.8 Turbo12.3 credits
A 1,000-character readGemini 3.1 Flash TTS8 creditsElevenLabs v4 Turbo9 creditsDeepgram Aura-27 creditsMiniMax Speech 2.8 Turbo13 credits
Longest scriptGemini 3.1 Flash TTS5,000 charactersElevenLabs v4 Turbo10,000 charactersDeepgram Aura-22,000 charactersMiniMax Speech 2.8 Turbo5,000 characters
VoicesGemini 3.1 Flash TTS30ElevenLabs v4 Turbo20Deepgram Aura-291MiniMax Speech 2.8 TurboBy voice id
OutputGemini 3.1 Flash TTSWAVElevenLabs v4 TurboRASTERDeepgram Aura-2RASTERMiniMax Speech 2.8 TurboRASTER

Prices are the catalog's, quoted before every render.

● Specs

Gemini 3.1 Flash TTS specs

StatusLive in the app, the API and the MCP
Made byGoogle
ModalityText to speech
InputsText script
Longest script5,000 characters
Voices30: Zephyr · Puck · Charon · Kore · Fenrir · Leda · Orus · Aoede · Callirrhoe · Autonoe · Enceladus · Iapetus · Umbriel · Algieba · Despina · Erinome · Algenib · Rasalgethi · Laomedeia · Achernar · Alnilam · Schedar · Gacrux · Pulcherrima and 6 more
Languages70+ languages
Temperature0–2
Audio tags200+, e.g. [sigh] [laughing] [whispering] [short pause] [long pause]
WatermarkSynthID, embedded by Google
Model statusPreview (Google's legacy preview of 3.1)
OutputWAV audio
Price7.5 credits per 1,000 characters · $0.031 per 1,000 characters on MAX yearly
A 1,000-character read8 credits

● How it works

How do you use Gemini 3.1 Flash TTS on OpenClips?

01

Describe it

Write the script, up to 5,000 characters. Every word is read aloud.

02

Pick a voice

30 voices. Play a sample, then keep the one that fits the script.

03

Pick the settings and generate

Choose the settings Gemini 3.1 Flash TTS offers, then generate. The result lands in your library.

● Tips

Tips for better results with Gemini 3.1 Flash TTS

  • Build the read from tags

    Google's formula: a pacing tag, some text, an expressive tag, more text, a pause tag. "[whispering] Listen. [long pause] Did you hear that?"

  • Try the temperature

    Temperature runs from 0 to 2. When a take sounds flat, read it again at another value and keep the best.

● Made for

What can you make with Gemini 3.1 Flash TTS?

StorytellingAudiobooksAudio descriptionsGame voicesNewscastsExplainersSocial readsNotifications

● Questions

Gemini 3.1 Flash TTS FAQ

Gemini 3.1 Flash TTS is a text-to-speech model by Google. Google's low-latency speech model, with 30 voices and expressive audio tags.

No. Google lists gemini-3.1-flash-tts-preview as a legacy preview and recommends Gemini 3.8 Flash TTS for new production work. OpenClips runs 3.1 Flash TTS on this page.

Google says 200+ audio tags. Examples from its docs: [sigh], [laughing], [whispering], [shouting], [short pause], [medium pause] and [long pause], written in square brackets in the script.

Yes. Google watermarks Gemini 3.1 Flash TTS audio with SynthID, an inaudible watermark that marks it as AI-generated.

Gemini 3.1 Flash TTS opens with your first purchase: any plan or credit pack. A new account still gets ⚡30 on signup with no card, for the models the free plan runs.

Gemini 3.1 Flash TTS costs 7.5 credits per 1,000 characters, paid from your OpenClips credits. That is from $0.031 per 1,000 characters on MAX yearly. A 1,000-character script costs 8 credits. The charge is the characters you send, rounded up once.

Up to 5,000 characters a read. A longer script is refused before any credit is held, so split a long script into reads.

30 voices: Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede, Callirrhoe, Autonoe, Enceladus, Iapetus, Umbriel, Algieba, Despina, Erinome, Algenib, Rasalgethi, Laomedeia, Achernar, Alnilam, Schedar, Gacrux, Pulcherrima and 6 more. Pick one per read.

70+ languages, as Google documents it.

An WAV file, saved to your library, ready to download or to drop on a video.

Per 1,000 characters: Gemini 3.1 Flash TTS 8 credits, ElevenLabs v4 Turbo 9 credits, Deepgram Aura-2 7 credits, MiniMax Speech 2.8 Turbo 13 credits. The table above sets their scripts, voices and files side by side.

Yes. Gemini 3.1 Flash TTS runs from the OpenClips app, the REST API and the MCP server, with the same settings and the same price.

● The receipts

Where do these Gemini 3.1 Flash TTS facts come from?

Every link goes to the vendor's own page.

Try Gemini 3.1 Flash TTS

30 voices, 70+ languages, tags for every pause.

Generate with Gemini 3.1 Flash TTS

What Gemini 3.1 Flash TTS does

Gemini 3.1 Flash TTS is Google's low-latency speech model, with steerable delivery through audio tags. On OpenClips you write up to 5,000 characters, pick one of 30 voices and get a WAV file in your library.

Directing the read with tags

Tags go in square brackets: [whispering], [laughing], [sigh], [short pause], [long pause]. Google's own advice is to alternate them with the text: a pacing tag, a line, an expressive tag, a line, a pause.

Gemini 3.1 Flash TTS vs the other voices

It is one of the cheapest voices per character on OpenClips, close to Deepgram Aura-2, but with tags for acted delivery. For the most polished read, compare it with ElevenLabs v4.