If there is any interest in this, Pushshift will soon provide API endpoints to do audio to text transcribing (at a combined aggregate rate of 10 minutes of audio per second). The upcoming API will also have convenience methods where you can provide a link to a youtube video and..
Conversation
Pushshift will fetch the audio for you and transcribe the audio into a JSON object that contains the transcribed text. The speech to text endpoints will include a parameter for multiple machine learning models and will be able to translate English, German, French, Spanish...
1
1
1
Chinese, Japanese and a dozen other languages. Once the new API endpoints are available, we will be beta testing the performance and during that time, all requests will be free of charge for research purposes. The goal will be to provide a better transcription service compared to
1
1
4
Google's cloud speech to text API. The AI also will have training capabilities along with automatic adaptive improvements. If you are interested in this, please let me know! We should have a beta API up within the next month (probably much sooner).
Replying to
this would be something pushshift is hosting? Not just a passthrough to some other transcription service? What technology is it built with?