Custom Voices

import os
import requests

# 1. Create the voice.
with open("reference.wav", "rb") as f:
    create = requests.post(
        "https://api.x.ai/v1/custom-voices",
        headers={"Authorization": f"Bearer {os.environ['XAI_API_KEY']}"},
        files={"file": ("reference.wav", f, "audio/wav")},
        data={
            "name": "Friendly Narrator",
            "language": "en",
            "gender": "female",
            "tone": "warm",
            "use_case": "narration",
        },
    )
create.raise_for_status()
voice_id = create.json()["voice_id"]

# 2. Synthesize speech with it.
speech = requests.post(
    "https://api.x.ai/v1/tts",
    headers={
        "Authorization": f"Bearer {os.environ['XAI_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "text": "Hello! This audio was synthesized using my custom voice.",
        "voice_id": voice_id,
        "language": "en",
    },
)
speech.raise_for_status()
with open("hello.mp3", "wb") as f:
    f.write(speech.content)

import fs from "fs";

// 1. Create the voice.
const form = new FormData();
form.append("file", new Blob([fs.readFileSync("reference.wav")]), "reference.wav");
form.append("name", "Friendly Narrator");
form.append("language", "en");
form.append("gender", "female");
form.append("tone", "warm");
form.append("use_case", "narration");

const createResp = await fetch("https://api.x.ai/v1/custom-voices", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.XAI_API_KEY}` },
  body: form,
});
if (!createResp.ok) throw new Error(`Create error ${createResp.status}`);
const { voice_id } = await createResp.json();

// 2. Synthesize speech with it.
const speech = await fetch("https://api.x.ai/v1/tts", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.XAI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    text: "Hello! This audio was synthesized using my custom voice.",
    voice_id,
    language: "en",
  }),
});
const buffer = Buffer.from(await speech.arrayBuffer());
fs.writeFileSync("hello.mp3", buffer);

import Foundation

let apiKey = ProcessInfo.processInfo.environment["XAI_API_KEY"]!

// 1. Create the voice.
let boundary = UUID().uuidString
var body = Data()

func appendField(_ name: String, _ value: String) {
    body.append("--\(boundary)\r\n".data(using: .utf8)!)
    body.append("Content-Disposition: form-data; name=\"\(name)\"\r\n\r\n".data(using: .utf8)!)
    body.append("\(value)\r\n".data(using: .utf8)!)
}

appendField("name", "Friendly Narrator")
appendField("language", "en")
appendField("gender", "female")
appendField("tone", "warm")
appendField("use_case", "narration")

let audioData = try Data(contentsOf: URL(fileURLWithPath: "reference.wav"))
body.append("--\(boundary)\r\n".data(using: .utf8)!)
body.append("Content-Disposition: form-data; name=\"file\"; filename=\"reference.wav\"\r\n".data(using: .utf8)!)
body.append("Content-Type: audio/wav\r\n\r\n".data(using: .utf8)!)
body.append(audioData)
body.append("\r\n--\(boundary)--\r\n".data(using: .utf8)!)

var request = URLRequest(url: URL(string: "https://api.x.ai/v1/custom-voices")!)
request.httpMethod = "POST"
request.setValue("Bearer \(apiKey)", forHTTPHeaderField: "Authorization")
request.setValue("multipart/form-data; boundary=\(boundary)", forHTTPHeaderField: "Content-Type")
request.httpBody = body

let (data, _) = try await URLSession.shared.upload(for: request, from: body)
let json = try JSONSerialization.jsonObject(with: data) as! [String: Any]
let voiceId = json["voice_id"] as! String

// 2. Synthesize speech with it.
var ttsRequest = URLRequest(url: URL(string: "https://api.x.ai/v1/tts")!)
ttsRequest.httpMethod = "POST"
ttsRequest.setValue("Bearer \(apiKey)", forHTTPHeaderField: "Authorization")
ttsRequest.setValue("application/json", forHTTPHeaderField: "Content-Type")
ttsRequest.httpBody = try JSONSerialization.data(withJSONObject: [
    "text": "Hello! This audio was synthesized using my custom voice.",
    "voice_id": voiceId,
    "language": "en",
])

let (audioBytes, _) = try await URLSession.shared.data(for: ttsRequest)
try audioBytes.write(to: URL(fileURLWithPath: "hello.mp3"))

import os
import requests

response = requests.get(
    "https://api.x.ai/v1/custom-voices",
    headers={"Authorization": f"Bearer {os.environ['XAI_API_KEY']}"},
    params={"limit": 50},
)
for voice in response.json()["voices"]:
    print(f"{voice['voice_id']:10s}  {voice.get('name')}")

const response = await fetch(
  "https://api.x.ai/v1/custom-voices?limit=50",
  { headers: { Authorization: `Bearer ${process.env.XAI_API_KEY}` } },
);
const { voices } = await response.json();
voices.forEach((v) => console.log(`${v.voice_id}  ${v.name}`));

import os
import requests

response = requests.patch(
    "https://api.x.ai/v1/custom-voices/nlbqfwie",
    headers={
        "Authorization": f"Bearer {os.environ['XAI_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={"description": "Updated after a tuning pass.", "tone": "calm"},
)
print(response.json())

const response = await fetch(
  "https://api.x.ai/v1/custom-voices/nlbqfwie",
  {
    method: "PATCH",
    headers: {
      Authorization: `Bearer ${process.env.XAI_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      description: "Updated after a tuning pass.",
      tone: "calm",
    }),
  },
);
if (!response.ok) throw new Error(`Update error ${response.status}: ${await response.text()}`);
console.log(await response.json());

import os
import requests

requests.delete(
    "https://api.x.ai/v1/custom-voices/nlbqfwie",
    headers={"Authorization": f"Bearer {os.environ['XAI_API_KEY']}"},
)

await fetch("https://api.x.ai/v1/custom-voices/nlbqfwie", {
  method: "DELETE",
  headers: { Authorization: `Bearer ${process.env.XAI_API_KEY}` },
});