SDKs & Libraries

SpeakEasy is fully compatible with the OpenAI API specification. That means any SDK or library built for the OpenAI audio endpoints works with SpeakEasy out of the box — you only need to change the base URL to https://api.tryspeakeasy.io/v1.

No custom SDK to install. No wrapper to learn. Pick the language you already use and start building.

Python (OpenAI SDK)

Install the official OpenAI Python package:

pip install openai

Speech-to-Text

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.tryspeakeasy.io/v1"
)

transcript = client.audio.transcriptions.create(
    model="whisper-large-v3",
    file=open("audio.mp3", "rb")
)

print(transcript.text)

Text-to-Speech

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.tryspeakeasy.io/v1"
)

response = client.audio.speech.create(
    model="tts-1",
    voice="alloy",
    input="Hello from SpeakEasy!"
)

response.stream_to_file("output.mp3")

Node.js (OpenAI SDK)

Install the official OpenAI Node.js package:

npm install openai

Speech-to-Text

import OpenAI from "openai";
import fs from "fs";

const openai = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.tryspeakeasy.io/v1",
});

const transcript = await openai.audio.transcriptions.create({
  model: "whisper-large-v3",
  file: fs.createReadStream("audio.mp3"),
});

console.log(transcript.text);

Text-to-Speech

import OpenAI from "openai";
import fs from "fs";

const openai = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.tryspeakeasy.io/v1",
});

const response = await openai.audio.speech.create({
  model: "tts-1",
  voice: "alloy",
  input: "Hello from SpeakEasy!",
});

const buffer = Buffer.from(await response.arrayBuffer());
fs.writeFileSync("output.mp3", buffer);

cURL

Speech-to-Text

curl -X POST https://api.tryspeakeasy.io/v1/audio/transcriptions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F "file=@audio.mp3" \
  -F "model=whisper-large-v3"

Text-to-Speech

curl -X POST https://api.tryspeakeasy.io/v1/audio/speech \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "voice": "alloy",
    "input": "Hello from SpeakEasy!"
  }' \
  --output output.mp3

JavaScript (fetch)

Speech-to-Text

const formData = new FormData();
formData.append("file", audioFile);
formData.append("model", "whisper-large-v3");

const response = await fetch("https://api.tryspeakeasy.io/v1/audio/transcriptions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
  },
  body: formData,
});

const data = await response.json();
console.log(data.text);

Text-to-Speech

const response = await fetch("https://api.tryspeakeasy.io/v1/audio/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "tts-1",
    voice: "alloy",
    input: "Hello from SpeakEasy!",
  }),
});

const audioBlob = await response.blob();
const audioUrl = URL.createObjectURL(audioBlob);

const audio = new Audio(audioUrl);
audio.play();

ElevenLabs SDK Compatibility

If you already use the ElevenLabs client library for text-to-speech, you can point it at SpeakEasy with a simple configuration change. The TTS endpoint accepts the same request format.

Python

from elevenlabs.client import ElevenLabs

client = ElevenLabs(
    api_key="YOUR_API_KEY",
    base_url="https://api.tryspeakeasy.io/v1"
)

audio = client.text_to_speech.convert(
    voice_id="alloy",
    text="Hello from SpeakEasy!",
    model_id="tts-1"
)

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

Node.js

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: "YOUR_API_KEY",
  baseUrl: "https://api.tryspeakeasy.io/v1",
});

const audioStream = await client.textToSpeech.convert("alloy", {
  text: "Hello from SpeakEasy!",
  model_id: "tts-1",
});

Other Languages

Don't see your language? Our REST API works with any HTTP client. Send requests to https://api.tryspeakeasy.io/v1 with your API key in the Authorization header and you're good to go. Check the Speech-to-Text and Text-to-Speech reference pages for full endpoint details.