Gemini 3.8 Flash TTS API

Google Gemini 3.8 Flash TTS: expressive speech in 30 voices with natural-language style control and inline vocal events like <laugh>.

Google·AudioAvailable

from$0.041/ 1K chars~~$0.045~~10% off

Model IDgemini-3.8-flash-tts

Try in Playground View API

text-to-speechvoice

Input

Text

Output

Audio

Provider

5 providers

Voice

Kore · Puck · Charon · Fenrir · Leda · Orus · Aoede · Zephyr · Callirrhoe · Autonoe · Enceladus · Iapetus · Umbriel · Algieba · Despina · Erinome · Algenib · Rasalgethi · Laomedeia · Achernar · Alnilam · Schedar · Gacrux · Pulcherrima · Achird · Zubenelgenubi · Vindemiatrix · Sadachbia · Sadaltager · Sulafat

Last 7 days · not enough recent requests for stats yet.

Gemini 3.8 Flash TTS pricing

Prices are per unit; requests without a provider are routed to the cheapest provider that supports your parameters.

Option	Price (USD)
All options	$0.041 / 1K chars 1 Credits~~$0.045~~10% off

Try Gemini 3.8 Flash TTS before you integrate

Test output quality, compare provider prices and estimate cost before writing any code.

Provider

Audio

Estimated cost

Input

Text*prompt

Voicevoice

Stylestyle_instructions

Result

Idle

Your generation will appear here.

Provider prices for this request

Enter a prompt to compare provider prices.

Gemini 3.8 Flash TTS prompt examples

Ready-to-use prompts. Load one into the playground and tweak it.

Source

Scene

6 prompts

You don’t have to rush. Some of the best moments happen when nothing important is supp

You don’t have to rush. Some of the best moments happen when nothing important is supposed to be happening. A quiet room, a warm drink, and a little time to yourself can be enough.

Friendly sign-off

Narration

Thanks for listening today. Go make something you're proud of, and we'll see you next week!

Calm meditation intro

Wellness

Find a comfortable seat and let your shoulders drop. Breathe in slowly... and let it go. There is nowhere else you need to be right now.

Product launch voiceover

Advertising

Meet the new Aurora headphones. Twenty hours of battery, studio-grade sound, and silence the moment you need it.

Story with a laugh

Character

I told him the map was upside down. <laugh> He still insisted we were heading north.

Have a wonderful day!

Gemini 3.8 Flash TTS API reference

Endpoints, request fields and runnable examples for this model.

Base URL

https://01router.com/api/v1

llms.txt

Quick start

Set API_KEY to your project key, then run a sample from your server. Replace example media URLs with your own public URLs.

Auto-routing chooses a provider that supports the request. Select a provider to see its input constraints and pinned request examples.

curl https://01router.com/api/v1/generations \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gemini-3.8-flash-tts",
  "input": {
    "prompt": "Welcome back. Let us get started.",
    "voice": "Kore"
  }
}
JSON

# Replace GENERATION_ID with the id returned above; poll until status is "succeeded" or "failed"
curl https://01router.com/api/v1/generations/GENERATION_ID -H "Authorization: Bearer $API_KEY"

Endpoints

Only endpoints relevant to this model are listed. Paths below include /api/v1. Click an endpoint to read its usage.

POST

/api/v1/generations

Create a generation (charges credits) · API key required

GET

/api/v1/generations/{id}

Get a generation; polls the provider while running · API key required

POST

/api/v1/generations/{id}/cancel

Cancel a running generation (credits refunded) · API key required

POST

/api/v1/quote

Price a request on every provider (no charge, no key needed) · Public · no key

GET

/api/v1/models/gemini-3.8-flash-tts

Get one model · Public · no key

Authentication

Send your API key as a Bearer token. Requests are billed to the key owner's credits.

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Get an API key

Input

Send JSON with Content-Type: application/json. Model parameters belong inside input; model, provider and callback_url are top-level fields.

Request body

Name	Type	Required	Description
model	string	Yes	"gemini-3.8-flash-tts"
provider	string	No	Pin a provider; omit to auto-route to the cheapest. One of: fal \| wavespeed \| kie \| vercel \| openrouter
input	object	Yes	Model parameters, see the input fields below.
callback_url	string	No	Optional public HTTPS webhook URL. The final task result is signed and delivered here; polling remains available.

input · input fields

Required fields are marked explicitly. Other fields use the listed defaults when omitted.

Name	Type	Required	Values	Default
prompt*	string	Yes	—	—
voice	string	No	Kore \| Puck \| Charon \| Fenrir \| Leda \| Orus \| Aoede \| Zephyr \| Callirrhoe \| Autonoe \| Enceladus \| Iapetus \| Umbriel \| Algieba \| Despina \| Erinome \| Algenib \| Rasalgethi \| Laomedeia \| Achernar \| Alnilam \| Schedar \| Gacrux \| Pulcherrima \| Achird \| Zubenelgenubi \| Vindemiatrix \| Sadachbia \| Sadaltager \| Sulafat	Kore
style_instructions e.g. "cheerful and friendly"; billing depends on the provider	string	No	—	—

Callbacks →

Output

Creating a task does not mean generation has finished. Keep its id, poll until succeeded or failed, then read outputs or error. Amounts below are illustrative; actual charges depend on the request.

queued→processing→succeeded / failed

Task submitted

{
  "id": "gen_example",
  "object": "generation",
  "model": "gemini-3.8-flash-tts",
  "type": "audio",
  "provider": "fal",
  "status": "processing",
  "input": {
    "prompt": "Welcome back. Let us get started.",
    "voice": "Kore"
  },
  "outputs": [],
  "error": null,
  "credits": 0,
  "price_usd": 0,
  "created_at": "2026-10-25T08:00:00.000Z",
  "completed_at": null
}

Task completed

{
  "id": "gen_example",
  "object": "generation",
  "model": "gemini-3.8-flash-tts",
  "type": "audio",
  "provider": "fal",
  "status": "succeeded",
  "input": {
    "prompt": "Welcome back. Let us get started.",
    "voice": "Kore"
  },
  "outputs": [
    "https://example.com/output.wav"
  ],
  "error": null,
  "credits": 0,
  "price_usd": 0,
  "created_at": "2026-10-25T08:00:00.000Z",
  "completed_at": "2026-10-25T08:01:00.000Z"
}

Response fields

Name	Type	Required	Description
id	string	Yes	Generation ID. Use it to query or cancel this task.
object	string	Yes	generation
model	string	Yes	gemini-3.8-flash-tts
type	string	Yes	audio
provider	string	Yes	Provider
status	string	Yes	queued → processing → succeeded / failed. Stop polling at either terminal state.
input	object	Yes	Model parameters, see the input fields below.
outputs	string[]	Yes	Result URLs. Empty while processing; read after succeeded and save the files promptly.
error	string \| null	Yes	Failure reason, or null when no failure is reported.
credits	number	Yes	Credits charged for this request.
price_usd	number	Yes	Request price in USD.
created_at	string	Yes	Creation time in ISO 8601 format.
completed_at	string \| null	Yes	Completion time in ISO 8601 format; null before completion.

Get the result

Poll every few seconds until status is succeeded or failed. Output URLs are provider-hosted and may expire — download them promptly. Or pass callback_url to get the result pushed.

curl "https://01router.com/api/v1/generations/GENERATION_ID" \
  -H "Authorization: Bearer $API_KEY"

queued → processing → succeeded / failed. Stop polling at either terminal state. Result URLs. Empty while processing; read after succeeded and save the files promptly.

Cancel a task

Cancellation depends on provider support and task state. A confirmed cancellation returns status: failed and error: Canceled by user. Unsupported or completed tasks return 409 not_cancelable.

curl -X POST "https://01router.com/api/v1/generations/GENERATION_ID/cancel" \
  -H "Authorization: Bearer $API_KEY"

Quote

Same body as creating a generation. Returns every available provider sorted by price, plus the ones that cannot serve the request and why.

curl "https://01router.com/api/v1/quote" -H "Content-Type: application/json" --data-binary @- <<'JSON'
{
  "model": "gemini-3.8-flash-tts",
  "input": {
    "prompt": "Welcome back. Let us get started.",
    "voice": "Kore"
  }
}
JSON

Model schema

This public endpoint returns the model parameters and each provider’s supported constraints and prices.

curl "https://01router.com/api/v1/models/gemini-3.8-flash-tts"

Errors

Check the HTTP status and error.message. Fix the request before retrying validation or authentication errors. A failed generation is reported in status and error on the task itself.

{
  "error": {
    "message": "Invalid or missing API key",
    "code": "unauthorized"
  }
}

400Invalid body or parameter value

401Missing or invalid API key

402Not enough credits

404Unknown model or generation

409The task cannot be canceled (already finished, or the provider does not support canceling)

429Too many requests — retry after the given seconds

502Every provider rejected the task (credits refunded)

Auth, routing, billing and error codes are covered in →

Use with AI

Give your coding assistant this model reference: endpoints, input constraints, output fields and request examples in plain text.

Open llms.txt

How does Gemini 3.8 Flash TTS compare?

Specs and starting prices side by side. Test with the same prompt before you choose.

	Gemini 3.8 Flash TTS	Suno V6	ElevenLabs Eleven v4	ElevenLabs Eleven v4 Turbo
Vendor	Google	Suno	ElevenLabs	ElevenLabs
Starting price	$0.041 / 1K chars	$0.045 / request	$0.072 / 1K chars	$0.036 / 1K chars
Input	Text	Text	Text	Text
Provider	5 providers	4 providers	3 providers	3 providers
Voice	Kore · Puck · Charon · Fenrir · Leda · Orus · Aoede · Zephyr · Callirrhoe · Autonoe · Enceladus · Iapetus · Umbriel · Algieba · Despina · Erinome · Algenib · Rasalgethi · Laomedeia · Achernar · Alnilam · Schedar · Gacrux · Pulcherrima · Achird · Zubenelgenubi · Vindemiatrix · Sadachbia · Sadaltager · Sulafat	—	undefined – undefined	undefined – undefined

Gemini 3.8 Flash TTS API FAQ

Which voices does Gemini 3.8 Flash TTS offer?

There are 30 prebuilt voices such as Kore (the default), Puck, Charon, Fenrir, Aoede and Zephyr. Pick one with the voice parameter; the playground lists them all.

How do I control tone and delivery?

Describe the delivery in style_instructions, for example "slow and calming" or "excited sports commentator". You can also place inline tags like <laugh> or <sigh> in the text.

How much text can I send in one request?

Keep a single request to a few thousand characters (provider limits are around 8,000 characters including style instructions). Split long scripts such as audiobook chapters into several requests.

What is it good for?

Narration and voiceovers, podcast intros, audiobooks, e-learning, in-app voice prompts and character voices for games.

How is it billed on 01router?

Depending on the provider, it is billed per 1,000 characters of text or per input/output token. The pricing table on this page lists each provider's rate, and requests without a provider go to the cheapest one. Failed generations are refunded.

Related models

Other models you can call with the same API key.

Audio · Suno

Suno V6

Suno V6 music generation: full songs with vocals or instrumentals from a description, or your own lyrics and style in custom mode. Each request returns two tracks.

from $0.045 / requestView API

Audio · ElevenLabs

ElevenLabs Eleven v4

ElevenLabs Eleven v4: expressive multilingual speech with audio tags, voice selection and delivery controls.

from $0.072 / 1K charsView API

Audio · ElevenLabs

ElevenLabs Eleven v4 Turbo

ElevenLabs Eleven v4 Turbo: expressive multilingual speech with audio tags, voice selection and delivery controls.

from $0.036 / 1K charsView API