Gemini 3.8 Flash TTS is Google's text-to-speech model, released 2026-09, and the successor to Gemini 3.1 Flash TTS Preview. It is the creative tier of the 3.8 TTS family, aimed at narration, character work, and multi-speaker dialogue where voice fidelity and acting nuance matter more than latency. It supports the 30 prebuilt studio voices along with Voice Design for custom voices from text descriptions and Voice Replication for cloning voices from short samples.
This model isn’t available on MirAPI yet, so the prices shown are the official list prices. Create an account to get notified when it goes live.
Modalities
inTextoutAudio
Price
$0.50/ 1M in
Context
33K
Released
Sep 23, 2026
Quick start
POST /v1/audio/speechimport os from openai import OpenAI client = OpenAI( base_url="https://api.mirapi.ai/v1", # changed api_key=os.environ["MIRAPI_API_KEY"], # changed ) with client.audio.speech.with_streaming_response.create( model="", voice="alloy", input="The quick brown fox jumped over the lazy dog.", ) as resp: resp.stream_to_file("speech.mp3")
import fs from "node:fs"; import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.mirapi.ai/v1", // changed apiKey: process.env.MIRAPI_API_KEY, // changed }); const mp3 = await client.audio.speech.create({ model: "", voice: "alloy", input: "The quick brown fox jumped over the lazy dog.", }); fs.writeFileSync("speech.mp3", Buffer.from(await mp3.arrayBuffer()));
curl https://api.mirapi.ai/v1/audio/speech \ -H "Authorization: Bearer $MIRAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "", "voice": "alloy", "input": "The quick brown fox jumped over the lazy dog." }' \ --output speech.mp3
Links
Wire Gemini 3.8 Flash TTS into your product
Start free1M free tokens to start, no card required. It’s OpenAI-compatible, so you only change the base URL.