Getting Started

Welcome to the SpeakEasy API documentation. SpeakEasy provides production-ready Speech-to-Text (STT) and Text-to-Speech (TTS) APIs with an OpenAI-compatible interface, so you can integrate high-quality speech processing into your applications in minutes.

Quickstart

Follow these three steps to make your first API call.

1. Sign Up

Create a free SpeakEasy account to get access to the API.

Create your account →

2. Get Your API Key

After signing in, navigate to the API Keyspage in your dashboard and generate a new key. Keep it safe — you will not be able to view the full key again.

export SPEAKEASY_API_KEY="sk-your-api-key"

3. Make Your First API Call

Transcribe an audio file with a single curl request:

curl https://api.tryspeakeasy.io/v1/audio/transcriptions \
  -H "Authorization: Bearer $SPEAKEASY_API_KEY" \
  -F file=@audio.mp3 \
  -F model=whisper-large-v3 \
  -F response_format=json

You should receive a JSON response containing the transcription:

{
  "text": "Hello, welcome to SpeakEasy."
}

Python Example

SpeakEasy is fully compatible with the OpenAI SDK. Just point the base_url to SpeakEasy and use your API key:

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.tryspeakeasy.io/v1",
)

# Transcribe an audio file (Speech-to-Text)
with open("audio.mp3", "rb") as f:
    transcript = client.audio.transcriptions.create(
        model="whisper-large-v3",
        file=f,
    )

print(transcript.text)

Available APIs

SpeakEasy offers two core APIs:

  • Speech-to-Text (STT) — Convert audio files or streams into accurate text transcriptions. Supports multiple languages, timestamps, and word-level detail.
  • Text-to-Speech (TTS) — Generate natural-sounding speech from text. Choose from a variety of voices and output formats.

Next Steps

Explore the rest of the documentation to get the most out of SpeakEasy:

  • Authentication— Learn about API key management, scopes, and secure token handling.
  • Error Codes— Understand error responses and how to handle them gracefully.
  • Rate Limits— Review request quotas, headers, and best practices for staying within limits.
  • SDKs & Libraries— Use official and community client libraries for Python, Node.js, and more.

$1. 50 hours. Both STT and TTS.

Your current speech API provider is charging you too much. Switch in one line of code.

SPEAKY