Live transcription
Delivers real-time audio-to-text transcription with ultra-low latency, purpose-built for live applications requiring real-time speech recognition.
Zoom Speech ranks among the top models on the Open ASR LeaderboardView leaderboard
Zoom AI Services: Scribe API
The world's most
accurate speech-to-text
API
Quality transcription you can trust, powered by Zoom’s ASR Model Pro.
Ranked as a top performing model on the HuggingFace Open ASR Leaderboard, Scribe API offers Live, Fast Sync and Batch Transcription services, built on the same ASR powering millions of Zoom meetings every day.
Capabilities
Everything you need for speech-to-text
From real-time to batch processing, Zoom Scribe API delivers transcription services with high accuracy and speed.
Fast sync transcription
Access synchronous, low-latency transcription for individual audio files. Process one file at a time with immediate response after completion.
Batch transcription
Process pre-recorded audio and video files at scale. Support for MP3, WAV, MP4, FLAC, OGG, and more with automatic format detection.
Use your own storage
Store your transcripts securely in your own AWS S3 bucket for enhanced data control and compliance.
Speaker diarization
Automatically label different speakers in multi-party conversations with high accuracy.
Broad language support
Transcribe in 36 languages and dialects with accent robust models trained on diverse datasets.
Multilingual model (New)
Multilingual model automatically listens, detects, and switches between languages on the fly in real time.
Custom dictionary support (New)
Add Dynamic or Persistent Dictionaries to ensure acronyms, product names, and domain jargon are transcribed correctly.
Premium Pro model (New)
Unlock our highest-accuracy English model for demanding transcription workloads that require maximum precision and performance.
Performance
Zoom Speech ranks among the top models on the Open ASR Leaderboard
Zoom’s Speech Recognition technology ranks among the top models on the Open ASR Leaderboard, a global benchmark for automatic speech recognition (ASR) performance. This milestone reflects our relentless pursuit of excellence in speech technology and the strength of Zoom AI Services' Scribe API.
Key model strengths include:
- Best-in-class accuracy: Our scalable innovation framework continuously enhances model quality, providing best-in-class transcription results where accuracy and readability matter most.
- Mastery of enterprise terminologies: Optimized for business and technical contexts, the model accurately handles company names, product terms, and domain-specific jargon — a critical advantage for meetings, support calls, and professional documentation.
- Reduced hallucinations: Zoom’s advanced modeling strategies minimize transcription “hallucinations” so what’s recognized truly reflects the speaker’s intent, not artificial or extraneous words.
Use cases
Built for every conversation
From boardrooms to contact centers, Zoom Scribe API transforms spoken words into actionable intelligence.
Contact Center analytics
Transcribe customer calls, detect sentiment, identify topics and surface insights to improve agent performance.
Media processing
Convert recordings into time-stamped transcripts and captions for editing & search.
Conversational intelligence applications
Integrate accurate speech-to-text into any conversational platform or app for virtual assistants and automated routing to deliver seamless customer self-service.
Enterprise knowledge management
Ingest and transcribe thousands of recorded meetings, town halls, and webinars to build centralized, instantly searchable corporate knowledge bases.
Edtech and course archiving
Asynchronously transcribe entire libraries of past lectures and online courses to create comprehensive study guides and ensure strict accessibility compliance.
Market research and qualitative analysis
Rapidly transcribe hundreds of hours of recorded focus groups, user interviews, and field studies to accelerate thematic analysis and reporting.
Try it
See the accuracy for yourself
Build and automate intelligent transcription workflows that can capture, structure, and summarize conversations across your business logic.
Sign-up or login is required to access the portal.
Try the playgroundDeveloper first
Start transcribing in minutes
- Simple, well-documented APIs
- REST API and OpenAPI spec
- Comprehensive error handling
- Webhook callbacks for async jobs
# Transcribe a file
curl -X POST \
https://api.zoom.us/v2/aiservices/scribe/transcribe \
-H "Authorization: Bearer $YOUR_JWT_TOKEN" \
-H "Content-Type: application/json" \
-d '{ "file": "{YOUR_AUDIO_URL}" }'import requests
# Transcribe a file
url = "https://api.zoom.us/v2/aiservices/scribe/transcribe"
headers = {
"Authorization": f"Bearer {YOUR_JWT_TOKEN}",
"Content-Type": "application/json"
}
data = {
"file": "{YOUR_AUDIO_URL}"
}
response = requests.post(url, headers=headers, json=data)
print(response.json())// Transcribe a file
const response = await fetch(
"https://api.zoom.us/v2/aiservices/scribe/transcribe",
{
method: "POST",
headers: {
"Authorization": `Bearer ${YOUR_JWT_TOKEN}`,
"Content-Type": "application/json"
},
body: JSON.stringify({
"file": "{YOUR_AUDIO_URL}"
})
}
);
const data = await response.json();
console.log(data);Pricing
Simple, transparent pricing
Apply prepaid credits to your use of Scribe API with transparent rates.
15¢/hour
Scribe API Batch processes all of your audio files from your storage and converts audio to text for scalable transcription workflows.
Scribe API Pro (Batch) model available at 30¢/hour
Usage is measured based on the total duration of audio processed in minutes during a given billing period.Get started20¢/hour
Scribe API Fast converts audio to text in seconds with enterprise-grade accuracy for near real-time applications.
Scribe API Pro (Fast) model available at 35¢/hour
Usage is measured based on the total duration of audio processed in minutes during a given billing period.Get started25¢/hour
Scribe API Live delivers real-time audio-to-text streaming with ultra-low latency, purpose-built for live applications requiring live speech recognition.
Scribe API Pro (Live) model available at 40¢/hour
Usage is measured based on the total duration of audio streamed and processed in minutes during a given billing period.Get startedAvailable Add-ons
Enhance your summaries with add-on capabilities that extend the Scribe API beyond its base plan.
Get startedLanguage Detection
4.8¢ / hour
Scribe API Language Detection continuously identifies the language being spoken and automatically switches the language used for transcription across available languages.
Available as an add-on with Scribe API.
Usage is measured based on the total duration of audio processed with language detection enabled in minutes during a given billing period.
Text Polishing
10.2¢ / hour
Scribe API Text Polishing refines spoken input into more concise, polished text by removing hesitations, repetitions, and filler words to produce clear, professional output.
Available as an add-on with Scribe API.
Usage is measured based on the total duration of audio processed with text polishing enabled in minutes during a given billing period.
Diarization
4.8¢ / hour
Scribe API Diarization automatically detects and labels individual speakers in audio recordings for meeting and call analysis. Available as an add-on for Scribe API Batch and Fast modes, and Speech Summarization API.
Available as an add-on with Scribe API.
Usage is measured based on the total duration of audio processed with speaker identification in minutes during a given billing period.
Developer resources
Everything you need to integrate, build, and ship with Zoom Scribe API.
