speech-to-text（语音转文字）

ElevenLabs Speech-to-Text

Transcribe audio to text with Scribe v2 - supports 90+ languages, speaker diarization, and word-level timestamps.

Setup: See Installation Guide. For JavaScript, use @elevenlabs/* packages only.

Quick Start

Python

from elevenlabs import ElevenLabs

client = ElevenLabs()

with open("audio.mp3", "rb") as audio_file:
    result = client.speech_to_text.convert(file=audio_file, model_id="scribe_v2")

print(result.text)

JavaScript

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

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"

Models

Transcription with Timestamps

Word-level timestamps include type classification and speaker identification:

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})")

Speaker Diarization

Identify WHO said WHAT - the model labels each word with a speaker ID, useful for meetings, interviews, or any multi-speaker audio:

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}")

For call recordings, the batch API can label diarized speakers as agent and customer by setting detect_speaker_roles=true alongside diarize=true. This option is not compatible with use_multi_channel=true.

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"

Keyterm Prompting

Help the model recognize specific words it might otherwise mishear - product names, technical jargon, or unusual spellings (up to 100 terms):

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

Language Detection

Automatic detection with optional language hint:

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%})")

Supported Formats

Audio: MP3, WAV, M4A, FLAC, OGG, WebM, AAC, AIFF, Opus Video: MP4, AVI, MKV, MOV, WMV, FLV, WebM, MPEG, 3GPP

Limits: Up to 3GB file size, 10 hours duration

Response Format

{
  "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"}
  ]
}

Word types:

• word - An actual spoken word
• spacing - Whitespace between words (useful for precise timing)
• audio_event - Non-speech sounds the model detected (laughter, applause, music, etc.)

Error Handling

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

Common errors:

• 401: Invalid API key
• 422: Invalid parameters
• 429: Rate limit exceeded

Tracking Costs

Monitor usage via request-id response header:

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')}")

Real-Time Streaming

For live transcription with ultra-low latency (~150ms), use the real-time API. The real-time API produces two types of transcripts:

• Partial transcripts: Interim results that update frequently as audio is processed - use these for live feedback (e.g., showing text as the user speaks)
• Committed transcripts: Final, stable results after you "commit" - use these as the source of truth for your application

A "commit" tells the model to finalize the current segment. You can commit manually (e.g., when the user pauses) or use Voice Activity Detection (VAD) to auto-commit on silence.

Python (Server-Side)

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,
    ) 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())

JavaScript (Client-Side with React)

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
    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>;
}

Commit Strategies

// 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,
  // 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",
  vad: {
    silenceThresholdSecs: 1.5,
    threshold: 0.4,
  },
});

Event Types

See real-time references for complete documentation.

References

• Installation Guide
• Transcription Options
• Real-Time Client-Side Streaming
• Real-Time Server-Side Streaming
• Commit Strategies
• Real-Time Event Reference