Seedance 2.0 is here - create consistent, multimodal AI videos faster with images, videos, and audio in one prompt.

Try Now
Skip to main content
scribe_v1 thumbnail

Scribe V1

by Elevenlabs

High-accuracy voice cloning technology with support for 99 languages, speaker diarization for up to 32 speakers, word-level timestamps, and dynamic audio tagging.

scribe_v1
Closed Source ModelLLMs.txtLearn more
API PlaygroundAPI Documentation

Input

File preview

or record audio

Per sec generation will cost $0.001

Output

Idle

Unknown content type

About Scribe V1

High-accuracy voice cloning technology with support for 99 languages, speaker diarization for up to 32 speakers, word-level timestamps, and dynamic audio tagging.

Technical Specifications

Model ID
scribe_v1
Provider
Elevenlabs
Category
Audio Models
Task
Voice Cloning
Price
$0.001000 per second
Added
June 30, 2025

Key Features

  • AI voice synthesis and text-to-speech
  • Multiple language and accent support
  • Voice cloning from short audio samples
  • Real-time audio processing via API
  • Customizable speech parameters

Quick Start

Integrate Scribe V1 into your application with a single API call. Get your API key from the pricing page to get started.

import requests
import json
url = "https://modelslab.com/api/v7/voice/speech-to-text"
headers = {
"Content-Type": "application/json"
}
data = {
"model_id": "scribe_v1",
"prompt": "your prompt here",
"key": "YOUR_API_KEY"
}
try:
response = requests.post(url, headers=headers, json=data)
response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX)
result = response.json()
print("API Response:")
print(json.dumps(result, indent=2))
except requests.exceptions.HTTPError as http_err:
print(f"HTTP error occurred: {http_err} - {response.text}")
except Exception as err:
print(f"Other error occurred: {err}")

View the full API documentation for SDKs, code examples in Python, JavaScript, and more.

Pricing

Scribe V1 API costs $0.001000 per second. Pay only for what you use with no minimum commitments. View pricing plans

Use Cases

  • Voice-over production for video content
  • Podcast and audiobook narration
  • Multilingual customer support automation
  • Interactive voice response (IVR) systems

Scribe V1 FAQ

High-accuracy voice cloning technology with support for 99 languages, speaker diarization for up to 32 speakers, word-level timestamps, and dynamic audio tagging.

You can integrate Scribe V1 into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "scribe_v1" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation.

Scribe V1 costs $0.001000 per second. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started.

The model ID for Scribe V1 is "scribe_v1". Use this ID in your API requests to specify this model.

Yes, ModelsLab offers a free tier that lets you try Scribe V1 and other AI models. Sign up to get free API credits and start building immediately.