Skip to main content
Breeze Developer Platform exposes the voice and text-to-speech capabilities behind Breeze Studio through a versioned HTTP API, official SDKs, and local developer tooling. Use these docs to create API keys, make your first request, understand voice workflows, and move from a first audio file to a production integration.

​
What you can build

Text to speech

Generate speech from text with saved voices, SDKs, or direct HTTP requests.

Voice Design

Create voice previews from natural-language direction and save the result for reuse.

Voice Clone

Create reusable voices from uploaded audio and manage the saved clone lifecycle.

Streaming

Stream synthesized audio as it is generated for agents and interactive voice products.

API Reference

Inspect the full HTTP API contract, generated examples, responses, and errors.

CLI Reference

Use Breeze CLI for local workflows, scripts, and agent-friendly automation.

​
First request

Install the Python SDK, export your API key, and synthesize audio. 
import os
from pathlib import Path

from breeze_blue import BreezeBlue, save

client = BreezeBlue(api_key=os.environ["BREEZE_API_KEY"])

audio = client.text_to_speech.convert(
    voice_id="voc_xeh3w54cqvnp",
    text="Hello from Breeze.",
    output_format="mp3",
)

save(audio, Path("out.mp3"))
Or use TypeScript: 
import { BreezeBlueClient } from "@breeze.blue/sdk";
import { save } from "@breeze.blue/sdk/node";

const client = new BreezeBlueClient({
  apiKey: process.env.BREEZE_API_KEY!,
});

const audio = await client.textToSpeech.convert(
  "voc_xeh3w54cqvnp",
  { text: "Hello from Breeze." },
  { outputFormat: "mp3" },
);

await save(audio, "out.mp3");

​
Documentation map

Start with the SDK quickstart, then move into API guides, API reference, CLI reference, errors, rate limits, and integration troubleshooting. The API contract continues to come from the Breeze Blue monorepo. SDK and CLI releases remain self-managed by the Breeze Blue engineering workflow.