บทสนทนาหลายผู้พูด

curl -X POST https://api.paxalabs.com/v1/tts/dialogue \
  -H "Authorization: Bearer $PAXA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "paxa-tts-flash-v2",
  "lines": [
    {
      "text": "สวัสดีครับ ยินดีต้อนรับสู่ Paxa Labs",
      "voice": "khanomkrok"
    },
    {
      "text": "สวัสดีค่ะ วันนี้ให้ช่วยเรื่องอะไรดีคะ",
      "voice": "nomyen"
    }
  ]
}' \
  --output dialogue.ndjson

import { writeFile } from "node:fs/promises";
import { createInterface } from "node:readline";
import { Readable } from "node:stream";

const response = await fetch("https://api.paxalabs.com/v1/tts/dialogue", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.PAXA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "paxa-tts-flash-v2",
    "lines": [
      {
        "text": "สวัสดีครับ ยินดีต้อนรับสู่ Paxa Labs",
        "voice": "khanomkrok"
      },
      {
        "text": "สวัสดีค่ะ วันนี้ให้ช่วยเรื่องอะไรดีคะ",
        "voice": "nomyen"
      }
    ]
  }),
});

if (!response.ok) throw new Error(`Request failed: ${response.status}`);
const audio: Buffer[][] = [];
let failure;
for await (const line of createInterface({ input: Readable.fromWeb(response.body!) })) {
  if (!line) continue;
  const event = JSON.parse(line);
  if (event.type === "error") failure = event;
  if (event.type === "chunk" && event.audio) {
    (audio[event.line] ??= []).push(Buffer.from(event.audio, "base64"));
  }
}
const kept = failure ? audio.slice(0, failure.lines.length) : audio;
await writeFile("dialogue.mp3", Buffer.concat(kept.flat()));
if (failure) throw new Error(failure.error.title);

import base64
import json
import os
import requests

response = requests.post(
    "https://api.paxalabs.com/v1/tts/dialogue",
    headers={"Authorization": f"Bearer {os.environ['PAXA_API_KEY']}"},
    json={
        "model": "paxa-tts-flash-v2",
        "lines": [
            {
                "text": "สวัสดีครับ ยินดีต้อนรับสู่ Paxa Labs",
                "voice": "khanomkrok",
            },
            {
                "text": "สวัสดีค่ะ วันนี้ให้ช่วยเรื่องอะไรดีคะ",
                "voice": "nomyen",
            },
        ],
    },
    stream=True,
)
response.raise_for_status()
audio = {}
failure = None
for line in response.iter_lines():
    if not line:
        continue
    event = json.loads(line)
    if event["type"] == "error":
        failure = event
    if event["type"] == "chunk" and event.get("audio"):
        audio.setdefault(event["line"], []).append(base64.b64decode(event["audio"]))
kept = len(failure["lines"]) if failure else len(audio)
with open("dialogue.mp3", "wb") as f:
    for index in range(kept):
        f.write(b"".join(audio.get(index, [])))
if failure:
    raise RuntimeError(failure["error"]["title"])

{"type":"chunk","line":0,"audio":"//NkxAAaOAAAAAABLBQAAAAAAABVVVVV..."}
{"type":"chunk","line":1,"audio":"//NkxAAaOAAAAAABLBQAAAAAAABVVVVV..."}
{"type":"done","lines":[{"start":0,"end":2.35},{"start":2.65,"end":4.9}]}