ElevenLabs Scribe v2

Configure ElevenLabs Scribe v2 Realtime for ultra-low latency speech-to-text with 90+ language support

ElevenLabs Scribe v2 Realtime is an ultra-low latency STT provider with ~150ms response time, 93.5% accuracy, and support for 90+ languages. It uses advanced Voice Activity Detection (VAD) for intelligent speech boundary detection.

---

Overview

Feature	Details
Model	scribe_v2_realtime
Latency	~150ms
Accuracy	93.5%
Languages	90+
VAD Support	✅ Advanced
Word Timestamps	✅ Optional
Language Detection	✅ Optional

---

Quick Start

1. Get API Key: Sign up at ElevenLabs and get your API key
2. Add to Provider Keys: Go to Settings → Provider Keys and add your ElevenLabs API key
3. Configure STT: In your assistant settings, select ElevenLabs as the STT provider

{
  "stt_settings": {
    "provider": "elevenlabs",
    "model": "scribe_v2_realtime",
    "language": "en"
  }
}

---

Configuration Options

Basic Settings

Parameter	Type	Default	Description
model	string	scribe_v2_realtime	The STT model to use
language	string	en	Language code (ISO 639-1 format)

VAD Settings

Voice Activity Detection (VAD) controls how the STT provider detects when someone has finished speaking.

Parameter	Type	Default	Range	Description
commit_strategy	string	vad	vad, manual	How transcripts are committed
vad_threshold	float	0.4	0.1 - 0.9	VAD sensitivity (lower = more sensitive)
vad_silence_threshold_secs	float	1.5	0.3 - 3.0	Silence duration to commit transcript
min_speech_duration_ms	int	100	50 - 2000	Minimum speech duration to consider
min_silence_duration_ms	int	100	50 - 2000	Minimum silence duration to consider

Additional Options

Parameter	Type	Default	Description
include_timestamps	boolean	true	Include word-level timestamps
include_language_detection	boolean	false	Include detected language in response

---

Full Configuration Example

{
  "stt_settings": {
    "provider": "elevenlabs",
    "model": "scribe_v2_realtime",
    "language": "en",
    "elevenlabs_config": {
      "commit_strategy": "vad",
      "vad_threshold": 0.4,
      "vad_silence_threshold_secs": 1.5,
      "min_speech_duration_ms": 100,
      "min_silence_duration_ms": 100,
      "include_timestamps": true,
      "include_language_detection": false
    }
  }
}

---

VAD Commit Strategy

ElevenLabs Scribe v2 uses a VAD-based commit strategy by default, which automatically detects when speech has ended and commits the transcript.

VAD vs Manual Commit

VAD (Voice Activity Detection) - Recommended:

• Automatically detects speech boundaries
• Commits transcript when silence is detected
• Best for natural conversation flow
• Configurable sensitivity and timing

Manual Commit:

• You control when transcripts are committed
• Useful for specific use cases where you need precise control
• Requires handling commit signals in your application

For phone calls, VAD commit strategy is recommended as it provides the most natural conversation experience.

---

VAD Tuning Guide

Adjusting VAD for Different Scenarios

Fast-Paced Conversations

{
  "vad_threshold": 0.3,
  "vad_silence_threshold_secs": 0.8,
  "min_speech_duration_ms": 50,
  "min_silence_duration_ms": 50
}

• Lower silence threshold for quicker responses
• More sensitive VAD detection

Patient/Thoughtful Speakers

{
  "vad_threshold": 0.5,
  "vad_silence_threshold_secs": 2.0,
  "min_speech_duration_ms": 150,
  "min_silence_duration_ms": 150
}

• Higher silence threshold to avoid cutting off
• More patience for pauses during thinking

Noisy Environments

{
  "vad_threshold": 0.6,
  "vad_silence_threshold_secs": 1.5,
  "min_speech_duration_ms": 200,
  "min_silence_duration_ms": 200
}

• Higher VAD threshold to filter noise
• Longer minimum durations to avoid false triggers

---

Supported Languages

ElevenLabs Scribe v2 supports 90+ languages. Use the ISO 639-1 language code:

Common Language Codes

Language	Code	Language	Code
English	en	Spanish	es
French	fr	German	de
Italian	it	Portuguese	pt
Dutch	nl	Polish	pl
Russian	ru	Japanese	ja
Korean	ko	Chinese	zh
Arabic	ar	Hindi	hi
Turkish	tr	Swedish	sv

For the full list of supported languages, visit the ElevenLabs documentation.

---

Word-Level Timestamps

When include_timestamps is enabled, each word in the transcript includes timing information:

{
  "text": "Hello, how can I help you today?",
  "words": [
    { "word": "Hello", "start": 0.0, "end": 0.45 },
    { "word": "how", "start": 0.52, "end": 0.68 },
    { "word": "can", "start": 0.70, "end": 0.85 },
    { "word": "I", "start": 0.87, "end": 0.92 },
    { "word": "help", "start": 0.95, "end": 1.15 },
    { "word": "you", "start": 1.18, "end": 1.32 },
    { "word": "today", "start": 1.35, "end": 1.72 }
  ]
}

Word timestamps are useful for analytics, keyword spotting, and advanced conversation analysis.

---

Best Practices

Start with Defaults

The default VAD settings work well for most phone call scenarios. Only adjust after testing.

Test with Real Calls

Record test calls and listen to the conversation flow. Adjust VAD settings based on actual user experience.

Match Call Style

Fast customer service? Lower thresholds. Complex discussions? Higher thresholds and more patience.

Enable Denoising

For noisy environments, enable audio denoising in your STT settings alongside VAD tuning.

---

Troubleshooting

Common Issues

Transcripts cut off mid-sentence:

• Increase vad_silence_threshold_secs (try 2.0 seconds)
• Increase min_silence_duration_ms

Long pauses before AI responds:

• Decrease vad_silence_threshold_secs (try 1.0 seconds)
• Lower vad_threshold for more sensitive detection

Background noise triggering false transcripts:

• Increase vad_threshold (try 0.6)
• Increase min_speech_duration_ms
• Enable audio denoising

Wrong language detected:

• Set the correct language code explicitly
• Disable include_language_detection if not needed

Connection issues:

• Verify your ElevenLabs API key in Settings → Provider Keys
• Check your account has sufficient credits

---

Comparison with Other Providers

Feature	ElevenLabs Scribe v2	Deepgram	Azure Speech
Latency	~150ms	~100ms	~200ms
Languages	90+	30+	100+
VAD	Advanced	Basic	Standard
Word Timestamps	✅	✅	✅
Term Boosting	❌	✅ Keywords	✅ Phrase Lists
Best For	Multi-language, VAD	Speed, English	Enterprise

Choose ElevenLabs Scribe v2 when you need excellent multi-language support with advanced VAD capabilities. Choose Deepgram for the absolute lowest latency, or Azure for enterprise features and custom models.