Google Gemini: Gemini 3.8 Flash-Lite TTS

Name: Gemini 3.8 Flash-Lite TTS
Author: Google Gemini

gemini/gemini-3-8-flash-lite-tts

active tts 1 provider

Playground

Google Gemini 3.8 Flash-Lite TTS (GA): fast, cost-efficient text-to-speech for high-throughput production, real-time voice-agent cascades and read-aloud features, sharing the 3.8 Flash TTS schema, 30 prebuilt voices, Extended Voice Library, voice design and voice replication.

AuthorGoogle Gemini

Languages101 languages

VoicesLoading...

Response formatsSynchronous: WAV · PCM · µ-law · A-law
Streaming: PCM · µ-law · A-law

Statusactive

Quick start

Gemini 3.8 Flash-Lite TTS

Create an API key

Create API key

Make a request

Pick an SDK, request mode, and language. The model and provider route are already filled in.

ElevenLabs SDK streaming TTS

Routes the ElevenLabs SDK through allmodels and streams the audio response.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const stream = await client.textToSpeech.stream("voice_id", {
  text: "I'm sorry, Dave. I'm afraid I can't do that.",
  modelId: "gemini/gemini-3-8-flash-lite-tts",
  outputFormat: "mp3_44100_128"
}, {
  queryParams: {
    provider: {
      "only": [
        "gemini"
      ]
    }
  }
});

const reader = stream.getReader();
for (;;) {
  const { done, value } = await reader.read();
  if (done) break;
  // Write value to your response, file, or audio playback pipeline.
}

Pass provider parameters

Pass provider preferences through the compatible SDK request options when you want to pin a route to a provider.

{
  queryParams: {
    provider: {
      only: ["gemini"]
    }
  }
}

Providers

Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.

ProviderSlugPer 1k charactersLatencyiModesUptime

Google Gemini 3 params

gemini

$0.02521

—

Synchronous

Supported languages

101 languages

Acehnese (Arab script) ace-Arab

Afrikaans af

Akan ak

Amharic am

Armenian hy

Assamese as

Awadhi awa

Balinese ban

Bangla bn

Banjar (Latn script) bjn-Latn

Basque eu

Belarusian be

Bhojpuri bho

Bosnian bs

Buginese bug

Bulgarian bg

Cantonese yue

Catalan ca

Cebuano ceb

Central Kurdish ckb

Chhattisgarhi hne

Chinese (Hans script) zh-Hans

Chinese (Hant script) zh-Hant

Croatian hr

Czech cs

Danish da

Dutch nl

Egyptian Arabic arz

English en

Estonian et

Filipino fil

French fr

Galician gl

Ganda lg

Georgian ka

German de

Greek el

Gujarati gu

Haitian Creole ht

Halh Mongolian khk

Hausa ha

Hebrew he

Hindi hi

Hungarian hu

Icelandic is

Iloko ilo

Indonesian id

Iranian Persian pes

Italian it

Japanese ja

Javanese jv

Kamba kam

Kannada kn

Kashmiri (Arab script) ks-Arab

Kashmiri (Deva script) ks-Deva

Kazakh kk

Khmer km

Kikuyu ki

Kinyarwanda rw

Kongo kg

Korean ko

Kyrgyz ky

Lao lo

Lingala ln

Macedonian mk

Magahi mag

Maithili mai

Malayalam ml

Maltese mt

Manipuri mni

Marathi mr

Minangkabau (Arab script) min-Arab

Mizo lus

Nepali (individual language) npi

Nigerian Fulfulde fuv

North Azerbaijani azj

Northern Sotho nso

Northern Uzbek uzn

Norwegian Bokmål nb

Norwegian Nynorsk nn

Nyanja ny

Odia (individual language) ory

Persian (Afghanistan) prs

Polish pl

Portuguese pt

Punjabi pa

Romanian ro

Russian ru

Santali sat

Serbian sr

Sinhala si

Slovak sk

South Azerbaijani azb

Southern Pashto pbt

Spanish es

Standard Arabic (Arab script) arb-Arab

Standard Arabic (Latn script) arb-Latn

Standard Latvian lvs

Standard Malay zsm

Tamil ta

Telugu te

Voices

Features

Text to speech

Generates spoken audio from a verbatim text transcript via the Interactions API (POST /v1beta/interactions, response_format.type 'audio') or generateContent (speech_metadata per part).

text_to_speech

Synchronous

One-shot synthesis returns the whole clip (WAV by default) in a single response.

synchronous

Streaming

stream: true on the Interactions API returns SSE step.delta audio chunks (headerless 24 kHz PCM by default) as they are synthesized.

streaming

Multilingual

Supports 101 documented languages; the model auto-detects the input language (voices are language-agnostic).

multilingual

Multi-speaker

Multi-speaker dialogue with up to 2 prebuilt-voice speakers per request (speech_config.speakers + per-turn speech_metadata.speaker; mode 'conversational').

multi_speaker

Style control

Turn-level delivery (emotion, pace, volume, accent) via speech_metadata.style, point-in-time vocal events via inline angle-bracket tags, and inline IPA pronunciation overrides.

style_control

Voice design

Custom vocal persona generated from a natural-language description (POST /v1beta/voices type='prompted'), returning a persistent voice_... id; 200 stored voices per project, 1-year TTL.

voice_design

Voice replication

Replicates a speaker from reference plus consent audio (POST /v1beta/voices type='replicated') as a persistent voice_... id or a stateless 7-day voicekey_... .

voice_cloning

Code

ElevenLabs SDK streaming TTS

Routes the ElevenLabs SDK through allmodels and streams the audio response.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const stream = await client.textToSpeech.stream("voice_id", {
  text: "I'm sorry, Dave. I'm afraid I can't do that.",
  modelId: "gemini/gemini-3-8-flash-lite-tts",
  outputFormat: "mp3_44100_128"
}, {
  queryParams: {
    provider: {
      "only": [
        "gemini"
      ]
    }
  }
});

const reader = stream.getReader();
for (;;) {
  const { done, value } = await reader.read();
  if (done) break;
  // Write value to your response, file, or audio playback pipeline.
}

Google Gemini: Gemini 3.8 Flash-Lite TTS

ElevenLabs SDK streaming TTS

Providers

Google Gemini

Pricing

Parameters

Supported languages

Voices

Features

Code

ElevenLabs SDK streaming TTS