The world’s most accurate API for AI- and human-generated transcripts
Trained from the most diverse collection of voices in the world, Rev AI sets the accuracy standard for video and voice applications.
What We Offer
Speech to Text
Asynchronous
- Submit audio or video files and get machine-generated transcripts in minutes
- High accuracy
- 58+ languages available
Streaming
- Generates transcription in real-time as audio or video is streamed
- 9 languages available
Human Transcription
- Get the highest level of accuracy from human-created transcripts
- ~24 hour turnaround time
- English only
Insights
Language Identification
- Predicts the dominant language used in an audio or video file
- 22 languages available
Sentiment Analysis
- Get positive, negative, and neutral statements from text
- English only
Topic Extraction
- Identify key topics in text
- Great for auto-tagging
- English only
Summarization
- Transform voice content into concise, actionable summaries
- English only
Translation
- Communicate across languages with context-aware translations
- 11 languages available
Forced Alignment
- Precise timestamps enhance content searchability and analysis
- English, Spanish, and French available
Why Rev AI
Lowest Word Error Rate, Highest Accuracy
Rev AI consistently outperforms other speech-to-text providers in accuracy for virtually every use case.
Least Bias for Gender and Ethnic accents
Rev AI's Word Error Rate (WER) is significantly lower than the competition on ethnic background, nationality, gender, and accent.
More Languages with lower WER
With 36 languages, address demand from customers around the globe.
Delivers the most readable transcripts
Rev AI transcripts have the highest readability, including proper grammar, punctuation, phone numbers, and addresses.
All in one STT and NLP solution
Rev AI offers a full suite of best-in-class speech-to-text and insights to power the exact quality and price your application requires.
World class Security Standards
Get the highest level of data control and security with SOC II, HIPAA, GDPR, and PCI compliance.
Overcome the limits of spoken word
Asynchronous
Speech to Text API
Audio transcription for pre-recorded audio.
Streaming
Speech to Text API
Real-time audio transcription.
Insights
Language Identification, Topic Extraction, Sentiment Analysis
Go beyond Speech to Text with actionable insights.
Benefits
Best-in-class accuracy
We train our speech models on 3 million+ hours of human-transcribed audio content to produce the most accurate API-driven, automatic speech recognition engine.
See how Rev AI compares to the competition
Ease of Implementation
Set-up and see results within an hour. Our collection of SDKs get you up and running in no time.
Flexible Deployment
Deploy Rev AI's speech-to-text engine in the cloud or on-prem according to your needs.
Reliability
We maintain 99.99% uptime and are on call to respond to security alerts and events.
Security
We handle your data with the care it deserves. All files are encrypted both at rest and in transit via industry best-practices.
Learn More
Simple integration
Our easy-to-use API is designed by developers for developers.
We provide you with SDKs, comprehensive documentation, and expert
support so you can get started in minutes. All you need to
generate your first transcript is an access token.
Explore Documentation
Python
Node
curl
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from rev_ai import apiclient as api | |
| from rev_ai.models.customer_url_data import CustomerUrlData | |
| # Create your client using your access token | |
| access_token = "your access token here" | |
| client = api.RevAiAPIClient(access_token) | |
| # Submit an audio file to Rev AI | |
| source_config = CustomerUrlData(url="https://www.rev.ai/FTC_Sample_1.mp3") | |
| job = client.submit_job_url(source_config=url) | |
| # Check your job's status | |
| details = client.get_job_details(job.id); | |
| # Retrieve your transcript | |
| transcript = client.get_transcript_text(job.id) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import { RevAiApiClient } from 'revai-node-sdk'; | |
| // Initialize your client with your access token | |
| const access_token = "your access token here"; | |
| const client = new RevAiApiClient(access_token); | |
| // Submit an audio file to Rev AI | |
| const options = { source_config: { url: "https://www.rev.ai/FTC_Sample_1.mp3" } }; | |
| const job = await client.submitJob(options); | |
| // Check your job's status | |
| const details = await client.getJobDetails(job.id); | |
| // Retrieve transcript | |
| const transcript = await client.getTranscriptText(job.id); |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| $ ACCESS_TOKEN=<your access token here> | |
| # Send an audio file to Rev AI | |
| $ curl -X POST https://api.rev.ai/speechtotext/v1/jobs \ | |
| -H "Authorization: Bearer ${ACCESS_TOKEN}" \ | |
| -H "Content-Type: application/json" \ | |
| -d "{'source_config':{'url':'https://www.rev.ai/FTC_Sample_1.mp3'}}" | |
| # Retrieve your transcript | |
| $ ID=<your job id here> | |
| $ curl -X GET https://api.rev.ai/speechtotext/v1/jobs/${ID}/transcript \ | |
| -H "Authorization: Bearer ${YOUR_ACCESS_TOKEN}" \ | |
| -H "Accept: application/vnd.rev.transcript.v1.0+json" |