＋ Add to collection

Install (CLI)

npx skillmds add elevenlabs/speech-to-text

Or Copy and Paste in Your Agent chat

Please install the Agent Skill "elevenlabs/speech-to-text" for me from skillmd.com. A SkillMD skill is a SKILL.md file — plain markdown plus a few companion files — that you save into my skills directory. Use whichever fetch route fits your setup: (1) if you have a terminal, run npx -y skillmds add elevenlabs/speech-to-text; (2) otherwise fetch the file manifest at https://api.skillmd.com/api/skills/elevenlabs/speech-to-text/bundle?format=manifest and download each listed file from its "url" into speech-to-text/ in your skills directory; (3) if the SkillMD MCP tools are connected, call skillmd_download with slug "elevenlabs/speech-to-text" and save the returned files under speech-to-text/. Show me the SKILL.md before saving if you'd like me to review it. If your skills directory is read-only (e.g. the Claude desktop app), save the files to a working folder instead and tell me — I'll add them through my app's skills settings.

README badge

Show this skill's registry status in your repo:

[![SkillMD](https://skillmd.com/badge/elevenlabs/speech-to-text.svg)](https://skillmd.com/skills/elevenlabs/speech-to-text)

speech-to-text

Name: speech-to-text
Rating: 4.2 (5 reviews)
Author: ElevenLabs

elevenlabs/speech-to-text · Agent Skill (multi-file)

by ElevenLabs · bundle

Published Jul 5, 2026 · Last updated Jul 6, 2026

Transcribe audio to text using ElevenLabs Scribe v2, supporting 90+ languages, speaker diarization, and word-level timestamps.

SKILL.md

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

Model ID	Description	Best For
`scribe_v2`	State-of-the-art accuracy, 90+ languages	Batch transcription, subtitles, long-form audio
`scribe_v2_realtime`	Low latency (~150ms)	Live transcription, voice agents

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.

If your workspace has registered speaker profiles, set use_speaker_library=true with diarize=true to match detected speakers against the speaker library.

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"

Multichannel Audio

Use use_multi_channel=true when each speaker is isolated on a separate audio channel. By default, the API returns one transcript per channel under transcripts; set multichannel_output_style="combined" to receive one transcript merged by timestamp, with channel_index on each word.

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

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 5.0GB 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,
        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())

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
    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 Recording</button>;
}

Commit Strategies

Strategy	Description
Manual	You call `commit()` when ready - use for file processing or when you control the audio segments
VAD	Voice Activity Detection auto-commits when silence is detected - use for live microphone input

Set includeLanguageDetection: true to receive the detected language code on committed transcript events that include timestamps.

// 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,
  },
});

Event Types

Event	Description
`partial_transcript`	Live interim results
`committed_transcript`	Final results after commit
`committed_transcript_with_timestamps`	Final with word timing
`error`	Error occurred

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

---
name: speech-to-text
description: Transcribe audio to text using ElevenLabs Scribe v2, supporting 90+ languages, speaker diarization, and word-level timestamps.
license: MIT
---

# ElevenLabs Speech-to-Text

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

> **Setup:** See [Installation Guide](references/installation.md). For JavaScript, use `@elevenlabs/*` packages only.

## Quick Start

### Python

```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

```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

```bash
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

| Model ID | Description | Best For |
|----------|-------------|----------|
| `scribe_v2` | State-of-the-art accuracy, 90+ languages | Batch transcription, subtitles, long-form audio |
| `scribe_v2_realtime` | Low latency (~150ms) | Live transcription, voice agents |

## Transcription with Timestamps

Word-level timestamps include type classification and speaker identification:

```python
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:

```python
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`.

If your workspace has registered speaker profiles, set `use_speaker_library=true` with `diarize=true` to match detected speakers against the speaker library.

```bash
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"
```

## Multichannel Audio

Use `use_multi_channel=true` when each speaker is isolated on a separate audio channel. By default, the API returns one transcript per channel under `transcripts`; set `multichannel_output_style="combined"` to receive one transcript merged by timestamp, with `channel_index` on each word.

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

## Keyterm Prompting

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

```python
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:

```python
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 5.0GB file size, 10 hours duration

## Response Format

```json
{
  "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

```python
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:

```python
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)

```python
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())
```

### JavaScript (Client-Side with React)

```typescript
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>;
}
```

### Commit Strategies

| Strategy | Description |
|----------|-------------|
| **Manual** | You call `commit()` when ready - use for file processing or when you control the audio segments |
| **VAD** | Voice Activity Detection auto-commits when silence is detected - use for live microphone input |

Set `includeLanguageDetection: true` to receive the detected language code on committed transcript
events that include timestamps.

```typescript
// 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
// 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,
  },
});
```

### Event Types

| Event | Description |
|-------|-------------|
| `partial_transcript` | Live interim results |
| `committed_transcript` | Final results after commit |
| `committed_transcript_with_timestamps` | Final with word timing |
| `error` | Error occurred |

See real-time references for complete documentation.

## References

- [Installation Guide](references/installation.md)
- [Transcription Options](references/transcription-options.md)
- [Real-Time Client-Side Streaming](references/realtime-client-side.md)
- [Real-Time Server-Side Streaming](references/realtime-server-side.md)
- [Commit Strategies](references/realtime-commit-strategies.md)
- [Real-Time Event Reference](references/realtime-events.md)

Files

This skill is a package of 7 files. Install with the command above, or download the folder.

📄SKILL.md entry
📁references
📄installation.md 2.1 KB
📄realtime-client-side.md 5.8 KB
📄realtime-commit-strategies.md 4.5 KB
📄realtime-events.md 5.4 KB
📄realtime-server-side.md 8.6 KB
📄transcription-options.md 9.7 KB

elevenlabs/skills/tree/main/speech-to-text commit · 80cd2f5356

▌
elevenlabs-stt · inference-sh
Transcribe audio with high accuracy using ElevenLabs Scribe models, supporting speaker diarization, audio event tagging, forced alignment, and subtitle generation via the inference.sh CLI.

584
repo stars
▌
transcribe · openai bundle
Transcribe audio files to text with optional speaker diarization and known-speaker hints using OpenAI models.

23.3k
repo stars
▌
whisper · orchestra-research bundle
Transcribe and translate speech across 99 languages using OpenAI's Whisper model, with support for multiple model sizes, batch processing, and subtitle generation.

10.4k
repo stars
▌
speech-to-text · inference-sh
Transcribe audio to text using ElevenLabs Scribe and Whisper models via the inference.sh CLI, supporting timestamps, speaker diarization, translation, and multi-language transcription.

584
repo stars
▌
text-to-speech · elevenlabs bundle
Generate natural speech from text using ElevenLabs voice AI, supporting 70+ languages, multiple models, and various output formats.

363
repo stars
▌
azure-ai-transcription-py · microsoft
Transcribe audio to text using Azure AI Transcription SDK with real-time and batch support, including timestamps and diarization.

2.7k
repo stars

Frequently asked questions

How do I install the speech-to-text skill?

Run npx skillmds add elevenlabs/speech-to-text in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the speech-to-text skill do?

Transcribe audio to text using ElevenLabs Scribe v2, supporting 90+ languages, speaker diarization, and word-level timestamps. It is listed under AI & ML, Coding & Dev Tools, Data & Analytics, Speech & Audio on SkillMD.

Is speech-to-text safe to use?

SkillMD's automated safety review verdict for this skill is CAUTION. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with speech-to-text?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is speech-to-text free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published speech-to-text?

ElevenLabs (@elevenlabs) published this skill as a verified publisher. Their other Agent Skills are listed on their SkillMD profile.