Generate Speech

POST /v1/talk/speech

curl -X POST "https://api.do.dev/v1/talk/speech" \
  -H "Authorization: Bearer do_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome to the Talk API! This is a demonstration of text-to-speech.",
    "voice": "aria",
    "format": "mp3",
    "speed": 1.0
  }' \
  --output output.mp3

{
  "error": "'text' is required and must be a string"
}

{
  "error": "'text' exceeds maximum length of 10,000 characters"
}

{
  "error": "Invalid voice: unknown. Valid voices: thalia, helena, aria, ..."
}

{
  "error": "'speed' must be a number between 0.5 and 2.0"
}

{
  "error": "API key required. Use Authorization: Bearer <key> or X-API-Key header."
}

{
  "error": "Rate limit exceeded"
}

curl -X POST "https://api.do.dev/v1/talk/speech" \
  -H "Authorization: Bearer do_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from my custom voice!",
    "customVoiceId": "your_elevenlabs_voice_id"
  }' \
  --output custom.mp3

async function generateSpeech(text, voice = "aria") {
  const response = await fetch("https://api.do.dev/v1/talk/speech", {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${API_KEY}`,
      "Content-Type": "application/json"
    },
    body: JSON.stringify({ text, voice })
  });

  if (!response.ok) {
    const error = await response.json();
    throw new Error(error.error);
  }

  // Play audio in browser
  const blob = await response.blob();
  const url = URL.createObjectURL(blob);
  const audio = new Audio(url);
  audio.play();

  return audio;
}

await generateSpeech("Hello, this is a test!", "aria");

import requests
import os

def generate_speech(text, voice="aria", format="mp3"):
    response = requests.post(
        "https://api.do.dev/v1/talk/speech",
        headers={
            "Authorization": f"Bearer {os.environ['DO_API_KEY']}",
            "Content-Type": "application/json"
        },
        json={
            "text": text,
            "voice": voice,
            "format": format
        }
    )
    response.raise_for_status()
    return response.content

audio = generate_speech("Hello, this is a test!")
with open("output.mp3", "wb") as f:
    f.write(audio)

import fs from "fs";

async function generateSpeech(text, voice = "aria", format = "mp3") {
  const response = await fetch("https://api.do.dev/v1/talk/speech", {
    method: "POST",
    headers: {
      "Authorization": `Bearer ${process.env.DO_API_KEY}`,
      "Content-Type": "application/json"
    },
    body: JSON.stringify({ text, voice, format })
  });

  if (!response.ok) {
    const error = await response.json();
    throw new Error(error.error);
  }

  return Buffer.from(await response.arrayBuffer());
}

const audio = await generateSpeech("Hello, this is a test!");
fs.writeFileSync("output.mp3", audio);