Multichannel speech-to-text

{
  "language_code": "en",
  "language_probability": 0.98,
  "text": "Hello world",
  "words": [...]
}

{
  "transcripts": [
    {
      "language_code": "en",
      "language_probability": 0.98,
      "text": "Hello from channel one.",
      "channel_index": 0,
      "words": [...]
    },
    {
      "language_code": "en",
      "language_probability": 0.97,
      "text": "Greetings from channel two.",
      "channel_index": 1,
      "words": [...]
    }
  ]
}

{
  "language_code": "en",
  "language_probability": 0.98,
  "text": "Hello from channel one. Greetings from channel two.",
  "words": [
    { "text": "Hello", "start": 0.0, "end": 0.5, "type": "word", "speaker_id": "speaker_0", "channel_index": 0 },
    { "text": "Greetings", "start": 0.6, "end": 1.2, "type": "word", "speaker_id": "speaker_1", "channel_index": 1 }
  ]
}

from elevenlabs import ElevenLabs

elevenlabs = ElevenLabs(api_key="YOUR_API_KEY")

def transcribe_multichannel(audio_file_path):
    with open(audio_file_path, 'rb') as audio_file:
        result = elevenlabs.speech_to_text.convert(
            file=audio_file,
            model_id='scribe_v2',
            use_multi_channel=True,
            diarize=False,
            timestamps_granularity='word'
        )
    return result

# Process the response

result = transcribe_multichannel('stereo_interview.wav')

if hasattr(result, 'transcripts'): # Multichannel response
    for transcript in result.transcripts:
        channel = transcript.channel_index
        text = transcript.text
        print(f"Channel {channel} (speaker_{channel}): {text}")
    else: # Single channel response (fallback)
        print(f"Text: {result.text}")

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import fs from "fs";

const elevenlabs = new ElevenLabsClient({
  apiKey: process.env.ELEVENLABS_API_KEY,
});

async function transcribeMultichannel(audioFilePath) {
  try {
    const audioFile = fs.createReadStream(audioFilePath);

    const result = await elevenlabs.speechToText.convert({
      file: audioFile,
      modelId: "scribe_v2",
      useMultiChannel: true,
      diarize: false,
      timestampsGranularity: "word",
    });

    // With useMultiChannel: true the SDK returns one transcript per channel
    result.transcripts.forEach((transcript) => {
      console.log(`Channel ${transcript.channelIndex}: ${transcript.text}`);
    });

    return result;
  } catch (error) {
    console.error("Error transcribing audio:", error);
    throw error;
  }
}

curl -X POST "https://api.elevenlabs.io/v1/speech-to-text" \
  -H "xi-api-key: YOUR_API_KEY" \
  -F "file=@stereo_audio_file.wav" \
  -F "model_id=scribe_v2" \
  -F "use_multi_channel=true" \
  -F "diarize=false" \
  -F "timestamps_granularity=word"

with open("stereo_interview.wav", "rb") as audio_file:
    result = elevenlabs.speech_to_text.convert(
        file=audio_file,
        model_id="scribe_v2",
        use_multi_channel=True,
        multichannel_output_style="combined",
        diarize=False,
        timestamps_granularity="word",
    )

for word in result.words:
    if word.type == "word":
        print(f"speaker_{word.channel_index}: {word.text}")

def process_large_multichannel_file(file_path, chunk_duration=300):
    """Process large files in chunks (5-minute segments)"""

    from pydub import AudioSegment
    from elevenlabs import ElevenLabs
    import os

    elevenlabs = ElevenLabs(api_key="YOUR_API_KEY")
    audio = AudioSegment.from_file(file_path)
    duration_ms = len(audio)
    chunk_size_ms = chunk_duration * 1000

    all_transcripts = []

    for start_ms in range(0, duration_ms, chunk_size_ms):
        end_ms = min(start_ms + chunk_size_ms, duration_ms)

        # Extract chunk
        chunk = audio[start_ms:end_ms]
        chunk_file = f"temp_chunk_{start_ms}.wav"
        chunk.export(chunk_file, format="wav")

        # Transcribe chunk using SDK
        with open(chunk_file, 'rb') as audio_file:
            result = elevenlabs.speech_to_text.convert(
                file=audio_file,
                model_id='scribe_v2',
                use_multi_channel=True,
                diarize=False,
                timestamps_granularity='word'
            )

        # Adjust timestamps
        if hasattr(result, 'transcripts'):
            for transcript in result.transcripts:
                for word in transcript.words or []:
                    word.start += start_ms / 1000
                    word.end += start_ms / 1000
            all_transcripts.extend(result.transcripts)

        # Clean up
        os.remove(chunk_file)

    return all_transcripts

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import { exec } from "child_process";
import fs from "fs";
import path from "path";
import { promisify } from "util";

const execAsync = promisify(exec);
const elevenlabs = new ElevenLabsClient({
  apiKey: process.env.ELEVENLABS_API_KEY,
});

async function processLargeMultichannelFile(filePath, chunkDuration = 300) {
  /**
   * Process large files in chunks (5-minute segments)
   * Requires ffmpeg to be installed
   */

  // Get audio duration using ffprobe
  const { stdout } = await execAsync(
    `ffprobe -v error -show_entries format=duration -of default=noprint_wrappers=1:nokey=1 "${filePath}"`
  );
  const durationSeconds = parseFloat(stdout);

  const allTranscripts = [];

  for (let startSeconds = 0; startSeconds < durationSeconds; startSeconds += chunkDuration) {
    const endSeconds = Math.min(startSeconds + chunkDuration, durationSeconds);
    const chunkFile = path.join(path.dirname(filePath), `temp_chunk_${startSeconds}.wav`);

    // Extract chunk using ffmpeg
    await execAsync(
      `ffmpeg -i "${filePath}" -ss ${startSeconds} -t ${chunkDuration} -c:a pcm_s16le "${chunkFile}" -y`
    );

    try {
      // Transcribe chunk
      const audioFile = fs.createReadStream(chunkFile);
      const result = await elevenlabs.speechToText.convert({
        file: audioFile,
        modelId: "scribe_v2",
        useMultiChannel: true,
        diarize: false,
        timestampsGranularity: "word",
      });

      // Adjust timestamps
      if (result.transcripts) {
        for (const transcript of result.transcripts) {
          for (const word of transcript.words || []) {
            word.start += startSeconds;
            word.end += startSeconds;
          }
        }
        allTranscripts.push(...result.transcripts);
      }
    } finally {
      // Clean up
      fs.unlinkSync(chunkFile);
    }
  }

  return { transcripts: allTranscripts };
}