Hive
About Hive’s Speech-to-Text Model
About Hive’s Speech-to-Text Model
Hive's Speech-to-Text Model ingests an audio stream and returns each word that was spoken, along with a confidence score and timestamp for that wo
We additionally return a fully punctuated transcript of the entire text. If you wish to use multiple languages, we also offer automatic language detection where you can pass in any audio clip and we'll identify/transcribe to the correct language automatically.
To learn about our moderation solutions, please see the Audio Moderation page.
Hive's Speech-to-Text Model ingests an audio stream and returns each word that was spoken, along with a confidence score and timestamp for that wo
We additionally return a fully punctuated transcript of the entire text. If you wish to use multiple languages, we also offer automatic language detection where you can pass in any audio clip and we'll identify/transcribe to the correct language automatically.
To learn about our moderation solutions, please see the Audio Moderation page.
Comprehensive coverage for diverse use cases
Comprehensive coverage for diverse use cases
Our deep learning model accurately detects and transcribes speech in several widely spoken languages.
Input : Audio, Video (mp4, webm, avi, flv, mkv, wmv, mov)
Response : Language classification, Punctuated transcript, Confidence scores and timestamps for each word
Language Support
Language Support
English
Spanish
Portuguese
French
Hindi
German
Arabic
Japanese
Simple usage based pricing so you only pay for what you use
Simple usage based pricing so you only pay for what you use
Speech-to-Text Model Pricing Details
Speech-to-Text Model Pricing Details
Model
Pricing
Unit
Speech to Text
$0.02
$0.02
Minute
How customers use our Speech-to-Text Model
How customers use our Speech-to-Text Model
Audio moderation
Social platforms screen videos, podcasts, and live streams to flag inappropriate language and
sensitive topics.Social platforms screen videos, podcasts, and live streams to flag inappropriate language and sensitive topics.
Captions
Video platforms generate captions for streams and full transcripts for podcasts and videos to improve accessibility.
Content tagging
Social apps and content platforms transcribe videos, podcasts, and live streams to identify content categories and improve recommendations.
Why choose our Speech-to-Text Model
Why choose our Speech-to-Text Model
Get more out of audio
Transcription data can easily be passed to text models to generate translations, moderate language, and more.
Simple integration
Model results are accessible with a single API call. Build our Speech-to-Text API into any application with just a few lines of code.
Proactive updates
Our Speech-to-Text model is regularly upgraded to improve performance, add commonly requested language support, and keep up with customer needs.
Get more out of audio
Transcription data can easily be passed to text models to generate translations, moderate language, and more.
Simple integration
Model results are accessible with a single API call. Build our Speech-to-Text API into any application with just a few lines of code.
Proactive updates
Our Speech-to-Text model is regularly upgraded to improve performance, add commonly requested language support, and keep up with customer needs.