Google TTS Standard

Specs & limits

The Standard voice tier of Google Cloud Text-to-Speech, grouped with WaveNet and Studio under Legacy TTS models on the pricing page. US$0.000004 per character (US$4 per 1 million characters) with the first 4 million characters free each month, the largest free allowance the pricing table publishes. Character counting (re-checked 2026-08-05): billable characters include spaces, newlines and all SSML tags except <mark>. Google's multi-byte note explicitly covers Standard: 'For WaveNet and Standard voices... Japanese (ja-JP) characters in UTF-8 typically require more than one byte each. In this case, you are only charged for one character, not multiple bytes.'

per Google official docs ↗

Use Google TTS Standard in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="google-tts-standard",
    messages=[{"role": "user", "content": "Summarize this diff"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://synthorai.io/v1",
  apiKey: "sk-syn-...",
});

const resp = await client.chat.completions.create({
  model: "google-tts-standard",
  messages: [{ role: "user", content: "Summarize this diff" }],
});
console.log(resp.choices[0].message.content);

curl https://synthorai.io/v1/chat/completions \
  -H "Authorization: Bearer sk-syn-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google-tts-standard",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go/v3"
	"github.com/openai/openai-go/v3/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://synthorai.io/v1"),
		option.WithAPIKey("sk-syn-..."),
	)
	resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
		Model: "google-tts-standard",
		Messages: []openai.ChatCompletionMessageParamUnion{
			openai.UserMessage("Summarize this diff"),
		},
	})
	fmt.Println(resp.Choices[0].Message.Content)
}

import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;

OpenAIClient client = OpenAIOkHttpClient.builder()
    .baseUrl("https://synthorai.io/v1")
    .apiKey("sk-syn-...")
    .build();

ChatCompletion resp = client.chat().completions().create(
    ChatCompletionCreateParams.builder()
        .model("google-tts-standard")
        .addUserMessage("Summarize this diff")
        .build());
System.out.println(resp.choices().get(0).message().content().orElse(""));

About Google TTS Standard

• Its voices are the oldest technology in the catalog and the docs say so plainly: parametric text-to-speech generates audio by passing outputs through signal processing algorithms known as vocoders, and many of the Standard voices use a variation of that technology, which is the honest reason they sound flatter than the generative tiers.
• The pricing page files Standard under Legacy TTS models next to WaveNet and Studio, at US$0.000004 per character, quoted as US$4 per 1 million characters, with the first 4 million characters each month free, the largest free allowance the pricing table publishes.
• What Standard gives up in expressiveness it makes up in reach.
• Voice ids follow a locale-plus-letter pattern such as en-US-Standard-A or cmn-CN-Standard-A, and the supported-voices table lists Standard across the widest locale span in the product, from af-ZA and eu-ES through hi-IN, ja-JP, and ur-IN to yue-HK, well beyond where the newer tiers reach.
• Controllability is SSML, with tags including speak, break, prosody, emphasis, say-as, sub, and phoneme, and the AudioConfig block adds speakingRate from 0.25 to 2.0, pitch across 20 semitones either way, volumeGainDb from -96 to 16, an optional output sample rate, and effectsProfileId device profiles tuned for wearables, handsets, headphones, Bluetooth speakers, car audio, and IVR.
• Output is LINEAR16 with a WAV header, 32 kbps MP3, OGG_OPUS, or G.711 MULAW and ALAW.
• Two constraints matter: a request carries at most 5,000 bytes of content, and Standard is not offered over streaming synthesis, so long text means the asynchronous Long Audio Synthesis path or your own chunking.
• Billing counts every character including spaces, newlines, and SSML tags except mark, though multi-byte characters count once for Standard.
• Synthorai serves it over the OpenAI-compatible /v1/audio/speech endpoint.

FAQ

Related models

Compare