Gemini 3.8 Flash TTSAI text to speech
Google's speech model: describe the delivery in style instructions. On Leap, it sits beside 174 other models in one studio.
- Text to speech
- No subscription
- Every top model, one account
- Pay per run, priced before it starts
Listen / An old sailor's ghost story
Read the transcript
We left the harbour with nine men aboard. We came back with nine men aboard. Trouble is... only eight of them were ours.
Listen / A sneaker-drop livestream host
Read the transcript
Doors open at noon, sizes are limited, and no, your cousin cannot hold your place in line. I can see you, Kevin.
Listen / A deadpan museum audio guide
Read the transcript
Room four. The artist completed this painting in a single night, and then spent eleven years telling everyone it took a single night.
AI text to speech
Gemini 3.8 Flash TTS at a glance
Gemini 3.8 Flash TTS is a text-to-speech model from Google. It makes speech from your text.
- Made by
- Makes
- Speech
- Starts from
- Your text
- Voices
- 30 to choose from
- Text
- Up to 4,000 characters
- Price
- $0.06075 per 1,000 characters
- Updated
- October 3, 2026
- 01Write the words, pick a voice
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Pick the right one
Gemini 3.8 Flash TTS and its siblings
| Model | Best for | Price per run |
|---|---|---|
| Gemini 3.8 Flash TTS (this page) | Google's speech model: describe the delivery in style instructions. | $0.06075 per 1,000 characters |
| Gemini 3.8 Flash-Lite TTS | Gemini's lighter speech model: 30 voices, directed in plain words. | $0.0513 per 1,000 characters |
Start with an idea
Three ways to try Gemini 3.8 Flash TTS
Side by side
More voice and sound models on Leap
Questions
Gemini 3.8 Flash TTS, answered
- What is Gemini 3.8 Flash TTS?
- Gemini 3.8 Flash TTS is a text-to-speech model from Google. Google's speech model: describe the delivery in style instructions. On Leap it runs in one studio beside every other top model, with one account.
- Which voices can I use?
- 30 voices, among them Kore, Achernar, Achird, Algenib and Algieba. You can hear each one in the studio before you run it.
- How much text can it read in one run?
- Up to 4,000 characters. You pay for the characters you send, with the price shown before you press go.
- How is it different from Gemini 3.8 Flash-Lite TTS?
- Gemini 3.8 Flash TTS: Google's speech model: describe the delivery in style instructions. Gemini 3.8 Flash-Lite TTS: Gemini's lighter speech model: 30 voices, directed in plain words. They all run in the same studio, so you can try one prompt on each.
- How much does a run cost?
- It costs $0.06075 per 1,000 characters. You see the exact price before you press go, and a run that fails costs nothing.
- Is Gemini 3.8 Flash TTS free to try?
- No. There is no free credit: you add credit from $5, and your first top-up has no card fee. It costs $0.06075 per 1,000 characters. You pay per run, in dollars, with no subscription.
- Can I use what I make commercially?
- Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
- Is there an API?
- Yes. Leap's REST API runs it as google/gemini-3.8-flash-tts, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
- Do I need a Google account?
- No. Leap sends your request to Google's model and gives you what it makes. One Leap account runs Gemini 3.8 Flash TTS and every other model, in the studio, through the API and from your agents.
Your idea, Gemini 3.8 Flash TTS.
Every run shows its price before it starts, and one that fails costs nothing.
Make it with Gemini 3.8 Flash TTSFor developers
Run Gemini 3.8 Flash TTS from code
- Model ID
- google/gemini-3.8-flash-tts
- Makes
- Voice and sound
- Pricing
- Per run, quoted first: POST /v1/quotes
Inputs
What the model takes. Leave out anything with a default.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "google/gemini-3.8-flash-tts", "input": { "text": "We left the harbour with nine men aboard. We came back with nine men aboard. Trouble is... only eight of them were ours." } }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"