2026年のおすすめTTS・STTアグリゲーターAPI

import { writeFile } from "node:fs/promises";

const response = await fetch("https://api.allmodels.io/oai/audio/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ALLMODELS_API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "grok/grok-tts",
    voice: "eve",
    input: "Your order has shipped. It arrives tomorrow.",
    response_format: "mp3"
  })
});

if (!response.ok) throw new Error(await response.text());
await writeFile("speech.mp3", Buffer.from(await response.arrayBuffer()));

import os

import requests

response = requests.post(
    "https://api.allmodels.io/oai/audio/speech",
    headers={"Authorization": f"Bearer {os.environ['ALLMODELS_API_KEY']}"},
    json={
        "model": "grok/grok-tts",
        "voice": "eve",
        "input": "Your order has shipped. It arrives tomorrow.",
        "response_format": "mp3",
    },
    timeout=60,
)
response.raise_for_status()

with open("speech.mp3", "wb") as output:
    output.write(response.content)

import { readFile } from "node:fs/promises";

const form = new FormData();
form.set("model", "deepgram/nova-3");
form.set("language", "en");
form.set("file", new Blob([await readFile("call.wav")], { type: "audio/wav" }), "call.wav");

const response = await fetch("https://api.allmodels.io/oai/audio/transcriptions", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.ALLMODELS_API_KEY}` },
  body: form
});

if (!response.ok) throw new Error(await response.text());
const transcript = await response.json();
console.log(transcript.text);

import os
import requests

with open("call.wav", "rb") as audio:
    response = requests.post(
        "https://api.allmodels.io/oai/audio/transcriptions",
        headers={"Authorization": f"Bearer {os.environ['ALLMODELS_API_KEY']}"},
        data={"model": "deepgram/nova-3", "language": "en"},
        files={"file": ("call.wav", audio, "audio/wav")},
        timeout=60,
    )

response.raise_for_status()
print(response.json()["text"])

import { writeFile } from "node:fs/promises";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseURL: "https://api.allmodels.io/oai"
});

const audio = await client.audio.speech.create({
  model: "grok/grok-tts",
  voice: "eve",
  input: "Your order has shipped. It arrives tomorrow.",
  response_format: "mp3"
});

await writeFile("speech.mp3", Buffer.from(await audio.arrayBuffer()));

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["ALLMODELS_API_KEY"],
    base_url="https://api.allmodels.io/oai",
)

audio = client.audio.speech.create(
    model="grok/grok-tts",
    voice="eve",
    input="Your order has shipped. It arrives tomorrow.",
    response_format="mp3",
)

audio.write_to_file("speech.mp3")

import { createReadStream } from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseURL: "https://api.allmodels.io/oai"
});

const transcript = await client.audio.transcriptions.create({
  file: createReadStream("call.wav"),
  model: "deepgram/nova-3",
  language: "en"
});

console.log(transcript.text);

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["ALLMODELS_API_KEY"],
    base_url="https://api.allmodels.io/oai",
)

with open("call.wav", "rb") as audio:
    transcript = client.audio.transcriptions.create(
        file=audio,
        model="deepgram/nova-3",
        language="en",
    )

print(transcript.text)

import { writeFile } from "node:fs/promises";
import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";

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

const audio = await client.textToSpeech.convert("eve", {
  text: "Your order has shipped. It arrives tomorrow.",
  modelId: "grok/grok-tts",
  outputFormat: "mp3_44100_128"
});

const chunks = await Array.fromAsync(audio, (chunk) => Buffer.from(chunk));
await writeFile("speech.mp3", Buffer.concat(chunks));

import os
from elevenlabs.client import ElevenLabs

client = ElevenLabs(
    api_key=os.environ["ALLMODELS_API_KEY"],
    base_url="https://api.allmodels.io/el",
)

audio = client.text_to_speech.convert(
    "eve",
    text="Your order has shipped. It arrives tomorrow.",
    model_id="grok/grok-tts",
    output_format="mp3_44100_128",
)

with open("speech.mp3", "wb") as output:
    for chunk in audio:
        output.write(chunk)

import { File } from "node:buffer";
import { readFile } from "node:fs/promises";
import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";

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

const bytes = await readFile("call.wav");
const transcript = await client.speechToText.convert({
  file: new File([bytes], "call.wav", { type: "audio/wav" }),
  modelId: "scribe_v2",
  languageCode: "en"
});

console.log(transcript.text);

import os
from elevenlabs.client import ElevenLabs

client = ElevenLabs(
    api_key=os.environ["ALLMODELS_API_KEY"],
    base_url="https://api.allmodels.io/el",
)

with open("call.wav", "rb") as audio:
    transcript = client.speech_to_text.convert(
        file=audio,
        model_id="deepgram/nova-3",
        language_code="en",
    )

print(transcript.text)