Asynchronous Speech-to-Text API for pre-recorded audio, powered by the world's leading speech recognition engine
Rev AI's asynchronous Speech-to-Text engine unlocks the power of voice for your business. Whether you're extracting insights from audio or transcribing content at scale, get it all done with a platform that is engineered for growth.
Get more out of your audio and video with our unmatched accuracy in an easy-to-use API
Rev AI serves your industry
Companies use Rev AI for a multitude of use cases, including business intelligence, market and user research, meeting transcription, and scaling of manual tasks.
Media and entertainment
Caption your videos at scale, increase the accessibility and searchability of you content, and improve video editing efficiency.
Legal and compliance
Use AI speech recognition for digital depositions, eDiscovery, call recording, risk analysis, and court reporting.
Education
Increase the accessibility of your lectures, webinars, and events with pre-recorded classes.
Call centers and analytics
Monitor agent quality, train agents, classify calls, and conduct post-call analytics to improve the customer experience while reducing operational costs.
Languages
Introducing Global Voice Recognition: Rev AI is available in 58 major world languages. We're bringing everything you already love about our English asynchronous ASR model to more global languages.
Read more
Asynchronous speech recognition features
Our global accent model supports major accents from around the world, eliminating the need to pay extra and switch models for different speakers and conversations. We provide you with the best ASR results out-of-the-box, regardless of who is speaking.
Fast delivery
We won't slow you down. Transcribe hour-long files in less than a minute.
Advanced punctuation and capitalization
We use natural language processing to produce transcripts that are highly accurate, fully punctuated, context-aware, and actually readable.
Timestamps
See the start time and end time for each word.
Speaker channel support
Seamlessly process audio on up to eight distinct speaker channels.
Custom vocabulary
Share unique names, industry-specific terminology, and more to improve the accuracy of your transcripts.
Accurate speaker separation
Recognize multiple speakers and attribute text to each in mono- and dual-channel audio.
Get a transcript in minutes
Once you receive your access token, send us your audio file using the /post endpoint.
Retrieve it in minutes with the /get endpoint.
Need more help? Check out our SDKs or chat with one of
our technical experts.
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" |