TTS-1

Specs & limits

Text-to-speech model optimized for speed: OpenAI documents tts-1 as the lower-latency, lower-quality option next to tts-1-hd. The instructions parameter that steers accent, emotion, intonation and tone on gpt-4o-mini-tts does not work with tts-1 or tts-1-hd.

per OpenAI official docs ↗

Use TTS-1 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="tts-1",
    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: "tts-1",
  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": "tts-1",
    "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: "tts-1",
		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("tts-1")
        .addUserMessage("Summarize this diff")
        .build());
System.out.println(resp.choices().get(0).message().content().orElse(""));

About TTS-1

• Its model page describes it as converting text to natural sounding spoken text and as tuned for realtime text-to-speech use cases, and the text-to-speech guide draws the family line plainly: tts-1 provides lower latency, but at a lower quality than tts-1-hd.
• It is a single-purpose model, supported only on the Audio API speech endpoint and on no other route, taking text in and returning audio, priced at $15 per million characters.
• Nine voices are available to it, a smaller set than the thirteen the Speech endpoint offers in total: alloy, ash, coral, echo, fable, onyx, nova, sage, and shimmer.
• Output can be MP3 by default, or Opus, AAC, FLAC, WAV, or raw 24 kHz PCM, and OpenAI recommends WAV or PCM for the fastest response; speech rate is adjustable from 0.25 to 4.0, with 1.0 the default, and audio can be streamed with chunked transfer encoding so playback begins before the full file exists.
• Two limits distinguish this generation from the newer one and will break copied code: the instructions parameter that steers accent, emotion, and delivery does not work on tts-1 or tts-1-hd, and the sse stream format is unsupported here.
• Language coverage generally follows Whisper's list of more than fifty languages, though the voices themselves are optimized for English, and OpenAI's usage policies require telling end users that the voice is AI-generated.
• Synthorai serves TTS-1 through its OpenAI-compatible /v1/audio/speech endpoint, so existing speech clients work unmodified.

FAQ

Related models

Compare