Direct the delivery in words
Add instructions such as 'Say cheerfully:' to the prompt, or use Style Instructions for tone, pace and accent.
Turn text into speech
Gemini 3.1 Flash Tts
Newest audio model from Google introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.
Made by Google20 creditsper run Pro
Opens the audio studio with Gemini 3.1 Flash Tts ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Gemini 3.1 Flash Tts makes, what it needs and what you get
What it makes
Turn text into speech
Reads your text aloud in a natural-sounding voice.
What you need
- The text to speak
What you get
A spoken audio clip of your text
About Gemini 3.1 Flash Tts
Gemini 3.1 Flash Tts is a Google text-to-speech (TTS) model that lets you direct how the speech sounds. You write your text in the Prompt field and get spoken audio back. You can put delivery instructions inside the prompt, such as 'Say cheerfully: Have a wonderful day!'. You can also use audio tags like [sigh], [laughing], [whispering] and [short pause].
Prompt is the only required input. Style Instructions is an optional box for tone, pace, accent and emotion, kept apart from your text. Language Code sets the language. If you leave it empty, the model detects the language from your text. Temperature runs from 0 to 2 and starts at 1. Higher values give more varied delivery, and lower values give more predictable delivery.
Speakers lets several voices read one script. Each speaker needs a voice and an alias, which is a short name. Start each line of your prompt with that name. Gemini 3.1 Flash Tts costs 20 credits.
Other models for this job
Same job: turn text into speech. Compare before you choose.
Audio Pro Open
CSM-1BTurn text into speech
CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.
Sesame100 creditsper run
Audio Pro Open
Kokoro TTS (Hindi)Turn text into speech
A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation.
Open Source100 creditsper run
Audio Pro Open
Kokoro TTS (Mandarin Chinese)Turn text into speech
A highly efficient Mandarin Chinese text-to-speech model that captures natural tones and prosody.
Open Source100 creditsper run
Audio Pro Open
Kokoro TTS (Japanese)Turn text into speech
A fast and natural-sounding Japanese text-to-speech model optimized for smooth pronunciation.
Open Source100 creditsper run
What it does well
Audio tags
Tags like [sigh], [laughing], [whispering] and [short pause] shape specific moments in the speech.
Several speakers
Speakers lets different voices read different parts of the text.
Language choice
Set a language with Language Code, or leave it empty and the model detects the language from your text.
How to use Gemini 3.1 Flash Tts
How It Works
How It Works
01
Write your prompt
Type the text to be spoken in Prompt. Add delivery instructions or audio tags if you want.
02
Set style and language
If you like, fill in Style Instructions, pick a Language Code, or change Temperature.
03
Generate
Run the model and the spoken audio comes back.
Tip For several voices, give each speaker a voice and an alias, which is a short name, in Speakers. Then start each line of your prompt with that name.
Good for
Expressive narration
Read a story or script aloud in the tone you ask for, such as cheerful or whispering.
Dialogue between characters
Give each character a voice in Speakers and write the script as separate lines.
Voice-over in another language
Pick one of the ten Language Code choices to have your text spoken in that language.
Questions
Quick answers to help you get the most out of Gemini 3.1 Flash Tts in FunAI Studio.
1. What do I need to provide?
2. Which languages can I choose?
3. What does it cost?