Realtime Server Side · Speech To Text · elevenlabs/skills · Skills Docs

Realtime Server Side · Speech To Text · elevenlabs/skills · Skills Docs

Purpose	Python / WebSocket	JavaScript
Limit language detection to expected additional languages	`secondary_languages`	`secondaryLanguages`
Return detected language in delayed final events	`include_language_detection`	`includeLanguageDetection`
Detect entities in committed segments	`entity_detection`	`entityDetection`
Reduce false activation from background speech and noise	`filter_background_audio`	`filterBackgroundAudio`
Disable history and logging for an enterprise zero-retention session	`enable_logging=False`	`enableLogging: false`

from dotenv import load_dotenv
import os
import asyncio
from elevenlabs import ElevenLabs
from elevenlabs import RealtimeEvents, RealtimeUrlOptions

load_dotenv()

async def main():
    elevenlabs = ElevenLabs(api_key=os.getenv("ELEVENLABS_API_KEY"))
    stop_event = asyncio.Event()

    connection = await elevenlabs.speech_to_text.realtime.connect(RealtimeUrlOptions(
        model_id="scribe_v2_realtime",
        url="https://npr-ice.streamguys1.com/live.mp3",
        include_timestamps=True,
        keyterms=["ElevenLabs", "Scribe"],
        no_verbatim=True,
    ))

    def on_partial_transcript(data):
        print(f"Partial: {data.get('text', '')}")

    def on_committed_transcript(data):
        print(f"Committed: {data.get('text', '')}")

    def on_error(error):
        print(f"Error: {error}")
        stop_event.set()

    def on_close():
        print("Connection closed")

    connection.on(RealtimeEvents.PARTIAL_TRANSCRIPT, on_partial_transcript)
    connection.on(RealtimeEvents.COMMITTED_TRANSCRIPT, on_committed_transcript)
    connection.on(RealtimeEvents.ERROR, on_error)
    connection.on(RealtimeEvents.CLOSE, on_close)

    try:
        await stop_event.wait()
    except KeyboardInterrupt:
        print("\nStopping transcription...")
    finally:
        await connection.close()

if __name__ == "__main__":
    asyncio.run(main())

import "dotenv/config";
import { ElevenLabsClient, RealtimeEvents } from "@elevenlabs/elevenlabs-js";

const elevenlabs = new ElevenLabsClient();

const connection = await elevenlabs.speechToText.realtime.connect({
  modelId: "scribe_v2_realtime",
  url: "https://npr-ice.streamguys1.com/live.mp3",
  includeTimestamps: true,
  keyterms: ["ElevenLabs", "Scribe"],
  noVerbatim: true,
});

connection.on(RealtimeEvents.PARTIAL_TRANSCRIPT, (transcript) => {
  console.log("Partial transcript", transcript);
});

connection.on(RealtimeEvents.COMMITTED_TRANSCRIPT, (transcript) => {
  console.log("Committed transcript", transcript);
});

connection.on(RealtimeEvents.ERROR, (error) => {
  console.log("Error", error);
});

connection.on(RealtimeEvents.CLOSE, () => {
  console.log("Connection closed");
});

import asyncio
import base64
import os
from dotenv import load_dotenv
from pathlib import Path
from elevenlabs import ElevenLabs
from elevenlabs import AudioFormat, CommitStrategy, RealtimeEvents, RealtimeAudioOptions
from pydub import AudioSegment

load_dotenv()

def load_and_convert_audio(audio_path: str | Path, target_sample_rate: int = 16000

import "dotenv/config";
import * as fs from "node:fs";
import { ElevenLabsClient, RealtimeEvents, AudioFormat } from "@elevenlabs/elevenlabs-js";

const elevenlabs = new ElevenLabsClient();

const connection = await elevenlabs.speechToText.realtime.connect({
  modelId: "scribe_v2_realtime",
  audioFormat: AudioFormat.PCM_16000,
  sampleRate: 16000,
  includeTimestamps: true,
});

connection.on(RealtimeEvents.SESSION_STARTED, (data) => {
  console.log("Session started", data);
  sendAudio();
});

connection.on(RealtimeEvents.PARTIAL_TRANSCRIPT, (transcript) => {
  console.log("Partial transcript", transcript);
});

connection.on(RealtimeEvents.COMMITTED_TRANSCRIPT, (transcript) => {
  console.log("Committed transcript", transcript);
});

connection.on(RealtimeEvents.COMMITTED_TRANSCRIPT_WITH_TIMESTAMPS, (transcript) => {
  console.log("Committed with timestamps", transcript);
});

connection.on(RealtimeEvents.ERROR, (error) => {
  console.log("Error", error);
});

connection.on(RealtimeEvents.CLOSE, () => {
  console.log("Connection closed");
});

async function sendAudio() {
  const pcmFilePath = "audio.pcm";
  const chunkSize = 32000;
  const audioBuffer = fs.readFileSync(pcmFilePath);
  const chunks: Buffer[] = [];

  for (let i = 0; i < audioBuffer.length; i += chunkSize) {
    const chunk = audioBuffer.subarray(i, i + chunkSize);
    chunks.push(chunk);
  }

  for (let i = 0; i < chunks.length; i++) {
    const chunk = chunks[i];
    const chunkBase64 = chunk.toString("base64");

    connection.send({
      audioBase64: chunkBase64,
      sampleRate: 16000,
    });

    if (i < chunks.length - 1) {
      await new Promise((resolve) => setTimeout(resolve, 1000));
    }
  }

  await new Promise((resolve) => setTimeout(resolve, 500));
  connection.commit();
}