ターン検出なしの OpenAI Realtime Transcription からの移行

pip install cartesia

npm i @cartesia/cartesia-js

import os
from cartesia import AsyncCartesia

client = AsyncCartesia(api_key=os.getenv("CARTESIA_API_KEY"))

async with client.stt.manual_finalize.websocket(
    model="ink-2", encoding="pcm_s16le", sample_rate=24000
) as connection:
    ...

import os
from cartesia import Cartesia

client = Cartesia(api_key=os.getenv("CARTESIA_API_KEY"))

with client.stt.manual_finalize.websocket(
    model="ink-2", encoding="pcm_s16le", sample_rate=24000
) as connection:
    ...

import Cartesia from "@cartesia/cartesia-js";

const client = new Cartesia({ apiKey: process.env.CARTESIA_API_KEY });

const connection = client.stt.manualFinalize.websocket({
  model: "ink-2",
  encoding: "pcm_s16le",
  sample_rate: 24000,
});

// Server-side: Generate access-tokens using your API key
import Cartesia from '@cartesia/cartesia-js';

const client = new Cartesia({ apiKey: process.env.CARTESIA_API_KEY });

export async function GET() {
  const { token } = await client.accessToken.create({
    grants: { stt: true, tts: false, agent: false },
    // How long the token lasts in seconds
    // Allowed values: 0–3600
    expires_in: 3600,
  });
  return Response.json({ token });
}


// Client-side
// 1. Fetch an access token from your server
// 2. Connect to Cartesia via WebSocket
import Cartesia from "@cartesia/cartesia-js";

async function getToken(): Promise<string> {
  const res = await fetch('/replace-with-your-server');
  const { token } = await res.json();
  return token;
}
const audioContext = new AudioContext();

const client = new Cartesia({ token: await getToken() });

const connection = client.stt.manualFinalize.websocket({
  model: "ink-2",
  encoding: "pcm_f32le",
  sample_rate: audioContext.sampleRate,
});

# raw_audio (bytes) - Raw audio data, about 100 ms at a time
await connection.send_raw(raw_audio)

# raw_audio (bytes) - Raw audio data, about 100 ms at a time
connection.send_raw(raw_audio)

// @param {ArrayBufferLike} rawAudio - raw audio data, about 100 ms at a time
connection.sendRaw(rawAudio);

from base64 import b64decode

await connection.send_raw(b64decode(audio_base_64))

from base64 import b64decode

connection.send_raw(b64decode(audio_base_64))

connection.sendRaw(Uint8Array.fromBase64(audioBase64));

# Commit input audio
await connection.send("finalize")

# Transcribe remaining audio, then close the socket
await connection.send("close")

# Commit input audio
connection.send("finalize")

# Transcribe remaining audio, then close the socket
connection.send("close")

// Commit input audio
connection.send("finalize");

// Transcribe remaining audio, then close the socket
connection.send("close");

import asyncio
from cartesia.types.stt import STTManualFinalizeWebsocketResponse

committed_transcript = ""

async def receive() -> None:
    global committed_transcript
    async for event in connection:
        if event.type == "transcript":
            if event.is_final:
              # Do not strip or add whitespace!
              committed_transcript += event.text
        elif event.type == "flush_done" or event.type == "done":
            print(f"Transcript: {committed_transcript}")
            committed_transcript = ""
        elif event.type == "error":
            print(f"error: {event.message}")

# Run receive() concurrently with your audio sender:
#   await asyncio.gather(send_audio(), receive())

from cartesia.types.stt import STTManualFinalizeWebsocketResponse

committed_transcript = ""

for event in connection:
    if event.type == "transcript":
        if event.is_final:
          # Do not strip or add whitespace!
          committed_transcript += event.text
    elif event.type == "flush_done" or event.type == "done":
        print(f"Transcript: {committed_transcript}")
        committed_transcript = ""
    elif event.type == "error":
        print(f"error: {event.message}")

import Cartesia from '@cartesia/cartesia-js';

let committedTranscript = '';

for await (const event of connection.stream()) {
  if (event.type === 'message') {
    const m = event.message;
    switch (m.type) {
      case 'transcript':
        if (m.is_final) {
          // Do not trim or add whitespace!
          committedTranscript += m.text;
        }
        break;
      case 'flush_done':
      case 'done':
        console.log(`Transcript: ${committedTranscript}`);
        committedTranscript = '';
        break;
    }
  } else if (event.type === 'error') {
    console.error(`error: ${event.error.message}`);
  }
}