speech-to-text

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import { createReadStream } from "fs";
 
const client = new ElevenLabsClient();
const result = await client.speechToText.convert({
  file: createReadStream("audio.mp3"),
  modelId: "scribe_v2",
});
console.log(result.text);

curl -X POST "https://api.elevenlabs.io/v1/speech-to-text" \
  -H "xi-api-key: $ELEVENLABS_API_KEY" -F "file=@audio.mp3" -F "model_id=scribe_v2"

result = client.speech_to_text.convert(
    file=audio_file, model_id="scribe_v2", timestamps_granularity="word"
)
 
for word in result.words:
    print(f"{word.text}: {word.start}s - {word.end}s (type: {word.type})")
 

result = client.speech_to_text.convert(
    file=audio_file,
    model_id="scribe_v2",
    diarize=True
)
 
for word in result.words:
    print(f"[{word.speaker_id}] {word.text}")

curl -X POST "https://api.elevenlabs.io/v1/speech-to-text" \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -F "file=@call.mp3" \
  -F "model_id=scribe_v2" \
  -F "diarize=true" \
  -F "detect_speaker_roles=true" \
  -F "use_speaker_library=true"

result = client.speech_to_text.convert(
    file=audio_file,
    model_id="scribe_v2",
    use_multi_channel=True,
    multichannel_output_style="combined",
)

result = client.speech_to_text.convert(
    file=audio_file,
    model_id="scribe_v2",
    keyterms=["ElevenLabs", "Scribe", "API"]
)

result = client.speech_to_text.convert(
    file=audio_file,
    model_id="scribe_v2",
    language_code="eng"  # ISO 639-1 or ISO 639-3 code
)
 
print(f"Detected: {result.language_code} ({result.language_probability:.0%})")

{
  "text": "The full transcription text",
  "language_code": "eng",
  "language_probability": 0.98,
  "words": [
    {"text": "The", "start": 0.0, "end": 0.15, "type": "word", "speaker_id": "speaker_0"},
    {"text": " ", "start": 0.15, "end": 0.16, "type": "spacing", "speaker_id": "speaker_0"}
  ]
}

try:
    result = client.speech_to_text.convert(file=audio_file, model_id="scribe_v2")
except Exception as e:
    print(f"Transcription failed: {e}")

response = client.speech_to_text.convert.with_raw_response(file=audio_file, model_id="scribe_v2")
result = response.parse()
print(f"Request ID: {response.headers.get('request-id')}")

import asyncio
from elevenlabs import ElevenLabs
 
client = ElevenLabs()
 
async def transcribe_realtime():
    async with client.speech_to_text.realtime.connect(
        model_id="scribe_v2_realtime",
        include_timestamps=True,
        keyterms=["ElevenLabs", "Scribe"],
        no_verbatim=True,
    ) as connection:
        await connection.stream_url("https://example.com/audio.mp3")
 
        async for event in connection:
            if event.type == "partial_transcript":
                print(f"Partial: {event.text}")
            elif event.type == "committed_transcript":
                print(f"Final: {event.text}")
 
asyncio.run(transcribe_realtime())

import { useScribe, CommitStrategy } from "@elevenlabs/react";
 
function TranscriptionComponent() {
  const [transcript, setTranscript] = useState("");
 
  const scribe = useScribe({
    modelId: "scribe_v2_realtime",
    commitStrategy: CommitStrategy.VAD, // Auto-commit on silence for mic input
    keyterms: ["ElevenLabs", "Scribe"],
    noVerbatim: true,
    includeLanguageDetection: true,
    onPartialTranscript: (data) => console.log("Partial:", data.text),
    onCommittedTranscript: (data) => setTranscript((prev) => prev + data.text),
  });
 
  const start = async () => {
    // Get token from your backend (never expose API key to client)
    const { token } = await fetch("/scribe-token").then((r) => r.json());
 
    await scribe.connect({
      token,
      microphone: { echoCancellation: true, noiseSuppression: true },
    });
  };
 
  return <button onClick={start}>Start Recording</button>;
}

// React: set commitStrategy on the hook (recommended for mic input)
import { useScribe, CommitStrategy } from "@elevenlabs/react";
 
const scribe = useScribe({
  modelId: "scribe_v2_realtime",
  commitStrategy: CommitStrategy.VAD,
  keyterms: ["ElevenLabs", "Scribe"],
  noVerbatim: true,
  // Optional VAD tuning:
  vadSilenceThresholdSecs: 1.5,
  vadThreshold: 0.4,
});

// JavaScript client: pass vad config on connect
const connection = await client.speechToText.realtime.connect({
  modelId: "scribe_v2_realtime",
  keyterms: ["ElevenLabs", "Scribe"],
  noVerbatim: true,
  vad: {
    silenceThresholdSecs: 1.5,
    threshold: 0.4,
  },
});