Rev Human Transcription API
Text-to-Speech task API
The Rev Human Transcription API service works with Text-to-Speech Natural Language Processing task. The Rev Human Transcription API enables developers to add human transcription services to applications. This API provides 99% accurate speech-to-text services, with all work done by humans. The output is in JSON format with beginning/ending timestamps on every word. Cost is $1.00 / audio minute, with 12 hour turnaround for files under 30 minutes. There are no minimums or contracts to get started. Developers may use Rev's API sandbox with no account creation required.
Specifications for version REST v1
The Rev Caption API provides human captions for $1.00 / audio minute. Revs Human Transcription API is the only API to offer the technical benefits of a speech-to-text API (JSON format per-word timestamps) with the accuracy of transcriptions done by humans.
Our transcribers are expected to research all terminology in the recording and can handle complicated terminology from any field. Yes apisupport@rev.com API Key 1 Recommended (active supported) Yes Web/Internet Single purpose API No REST JSON URI Query String/CRUD XML JSON XML No No No
Share to help more people.
Classify and extract text 10x better and faster 🦾
Metatext helps you to classify and extract information from text and documents with customized language models with your data and expertise.