リアルタイム音声

import { Phaseo, RealtimeSessionClosedError } from "@phaseo/sdk";

const client = new Phaseo({ apiKey: process.env.PHASEO_API_KEY });

const session = await client.realtime.connect({
  model: "openai/gpt-realtime-2",
  voice: "marin",
  instructions: "Answer in one sentence.",
});

session.onWarning((warning) => console.warn(warning.code, warning.message));
session.on("response.output_audio.delta", (event) => play(event.delta as string));

// PCM16 microphone audio: 24 kHz for OpenAI and xAI, 16 kHz for Google.
session.sendAudio(pcm16Chunk);

try {
  const ended = await session.end({ reason: "caller hung up" });
  console.log(ended.reason, ended.duration_seconds, ended.cost.total_usd, ended.billing_status);
} catch (error) {
  if (error instanceof RealtimeSessionClosedError) {
    // The call is still billed. Fetch the final cost later with error.finalBill.path.
    console.error(error.message);
  } else {
    throw error;
  }
}

import asyncio
from phaseo import AsyncPhaseo, RealtimeSessionClosedError

async def main(pcm16_chunk: bytes) -> None:
    client = AsyncPhaseo()  # reads PHASEO_API_KEY
    session = await client.realtime.connect(
        "openai/gpt-realtime-2", voice="marin", instructions="Answer in one sentence."
    )
    session.on_warning(lambda warning: print("warning", warning["code"]))

    # PCM16 microphone audio: 24 kHz for OpenAI and xAI, 16 kHz for Google.
    await session.send_audio(pcm16_chunk)

    try:
        ended = await session.end(reason="caller hung up")
        print(ended["reason"], ended["duration_seconds"], ended["cost"]["total_usd"], ended["billing_status"])
    except RealtimeSessionClosedError as error:
        # The call is still billed. Fetch the final cost later with error.final_bill["path"].
        print(error)
    finally:
        await client.close()

import (
  "context"
  "errors"
  "log"

  phaseo "github.com/phaseoteam/Phaseo/packages/sdk/sdk-go/v3"
  "github.com/phaseoteam/Phaseo/packages/sdk/sdk-go/v3/realtime"
)

ctx := context.Background()
client, err := phaseo.NewFromEnv()
if err != nil {
  return err
}

session, err := realtime.Connect(ctx, client, realtime.Options{
  Model:        "openai/gpt-realtime-2",
  Voice:        "marin",
  Instructions: "Answer in one sentence.",
})
if err != nil {
  return err
}

session.OnWarning(func(w realtime.Warning) { log.Println(w.Code, w.Message) })

// PCM16 microphone audio: 24 kHz for OpenAI and xAI, 16 kHz for Google.
_ = session.SendAudio(ctx, pcm16Chunk)

ended, err := session.End(ctx, realtime.EndOptions{Reason: "caller hung up"})
var closed *realtime.ClosedError
if errors.As(err, &closed) {
  // The call is still billed. Fetch the final cost later with closed.FinalBill.Path.
  log.Println(closed)
} else if err != nil {
  return err
} else {
  log.Println(ended.Reason, ended.DurationSeconds, ended.Cost.TotalUSD, ended.BillingStatus)
}

using PhaseoSdk;

var client = new Phaseo();

var session = await client.Realtime.ConnectAsync(new RealtimeConnectOptions
{
    Model = "openai/gpt-realtime-2",
    Voice = "marin",
    Instructions = "Answer in one sentence.",
});

using var warnings = session.OnWarning(warning => Console.WriteLine(warning.GetProperty("code").GetString()));

// PCM16 microphone audio: 24 kHz for OpenAI and xAI, 16 kHz for Google.
await session.SendAudioAsync(pcm16Chunk);

try
{
    var ended = await session.EndAsync(reason: "caller hung up");
    Console.WriteLine(ended.GetProperty("billing_status").GetString());
}
catch (RealtimeSessionClosedException error)
{
    // The call is still billed. Fetch the final cost later with error.FinalBillPath.
    Console.Error.WriteLine(error.Message);
}

<?php
require 'vendor/autoload.php';

use Phaseo\Sdk\Phaseo;
use Phaseo\Sdk\RealtimeSessionClosedException;

$client = new Phaseo();

$session = $client->realtime()->connect([
    'model' => 'openai/gpt-realtime-2',
    'voice' => 'marin',
    'instructions' => 'Answer in one sentence.',
]);

$session->onWarning(fn (array $warning) => error_log($warning['code']));

// PCM16 microphone audio: 24 kHz for OpenAI and xAI, 16 kHz for Google.
$session->sendAudio($pcm16Chunk);

try {
    $ended = $session->end(reason: 'caller hung up');
    echo $ended['reason'], ' ', $ended['cost']['total_usd'], ' ', $ended['billing_status'], PHP_EOL;
} catch (RealtimeSessionClosedException $error) {
    // The call is still billed. Fetch the final cost later with $error->getFinalBillPath().
    error_log($error->getMessage());
}

require 'phaseo_sdk'

client = PhaseoSdk::Phaseo.new

session = client.realtime.connect(
  model: 'openai/gpt-realtime-2',
  voice: 'marin',
  instructions: 'Answer in one sentence.'
)

session.on_warning { |warning| warn warning['code'] }

# PCM16 microphone audio: 24 kHz for OpenAI and xAI, 16 kHz for Google.
session.send_audio(pcm16_chunk)

begin
  ended = session.end(reason: 'caller hung up')
  puts ended['reason'], ended['cost']['total_usd'], ended['billing_status']
rescue PhaseoSdk::RealtimeSessionClosedError => error
  # The call is still billed. Fetch the final cost later with error.final_bill_path.
  warn error.message
end

import app.phaseo.sdk.Phaseo;
import app.phaseo.sdk.RealtimeSession;
import app.phaseo.sdk.RealtimeSessionClosedException;
import com.fasterxml.jackson.databind.JsonNode;
import java.time.Duration;
import java.util.Map;

Phaseo client = new Phaseo(System.getenv("PHASEO_API_KEY"));

RealtimeSession session = client.realtime.connect(Map.of(
    "model", "openai/gpt-realtime-2",
    "voice", "marin",
    "instructions", "Answer in one sentence."));

session.onWarning(warning -> System.out.println(warning.path("code").asText()));
session.on("response.output_audio.delta", event -> play(event.path("delta").asText()));

// PCM16 microphone audio: 24 kHz for OpenAI and xAI, 16 kHz for Google.
session.sendAudio(pcm16Chunk);

try {
    JsonNode ended = session.end("caller hung up", null, Duration.ofSeconds(60));
    System.out.println(ended.path("billing_status").asText());
} catch (RealtimeSessionClosedException error) {
    // The call is still billed. Fetch the final cost later with error.finalBillPath().
    System.err.println(error.getMessage());
}

use phaseo::Phaseo;
use phaseo::realtime::{EndOptions, RealtimeError, RealtimeOptions};

fn talk(pcm16_chunk: &[u8]) -> Result<(), Box<dyn std::error::Error>> {
    let client = Phaseo::from_env()?;

    let session = client.realtime().connect(
        RealtimeOptions::new("openai/gpt-realtime-2")
            .voice("marin")
            .instructions("Answer in one sentence."),
    )?;

    session.on_warning(|warning| eprintln!("{}", warning["code"]));

    // PCM16 microphone audio: 24 kHz for OpenAI and xAI, 16 kHz for Google.
    session.send_audio(pcm16_chunk)?;

    match session.end(EndOptions { reason: Some("caller hung up".into()), ..EndOptions::default() }) {
        Ok(ended) => println!("{} {}", ended["cost"]["total_usd"], ended["billing_status"]),
        // The call is still billed. Fetch the final cost later with final_bill_path.
        Err(RealtimeError::Closed { final_bill_path, .. }) => eprintln!("bill later: GET {final_bill_path}"),
        Err(error) => return Err(error.into()),
    }
    Ok(())
}

for await (const event of session) {
  if (event.type === "session.ended") console.log("bill", event.cost);
}

async for event in session:
    if event["type"] == "response.output_audio.delta":
        play(event["delta"])

for event := range session.Events() {
  if event.Type() == "response.output_audio.delta" {
    play(event["delta"].(string))
  }
}

await foreach (var item in session.EventsAsync())
{
    if (item.GetProperty("type").GetString() == "response.output_audio.delta")
        Play(item.GetProperty("delta").GetString()!);
}

foreach ($session->events() as $event) {
    if ($event['type'] === 'response.output_audio.delta') {
        play($event['delta']);
    }
}

session.each_event do |event|
  play(event['delta']) if event['type'] == 'response.output_audio.delta'
end

for (JsonNode event : session.events()) {
    if (event.path("type").asText().equals("response.output_audio.delta")) {
        play(event.path("delta").asText());
    }
}

// events() queues every event, audio deltas included, until you receive it.
// Drain it in its own thread, or drop it once you're done.
let events = session.events();
let reader = std::thread::spawn(move || {
    for event in events {
        println!("{}", event["type"]);
    }
});