exemplaryai/ai-engine

Easy to use Multi-Provider ASR/Speech To Text and NLP engine

27
/ 100
Experimental

This project helps developers integrate various Speech-to-Text (ASR) and Natural Language Processing (NLP) services into their applications without dealing with each provider's unique API. It takes audio or video files as input and outputs standardized transcripts along with insights like sentiment, questions, and entities. This is for developers building conversational AI applications, transcription services, or analysis tools that rely on understanding spoken language.

No commits in the last 6 months.

Use this if you are a developer who needs to process audio files into text and extract meaning from them, and you want the flexibility to easily switch between or combine different commercial AI providers like Deepgram, AssemblyAI, or AWS Comprehend.

Not ideal if you are a non-technical user looking for a ready-to-use transcription service or an application that analyzes audio without needing to write code.

conversational-ai speech-recognition audio-transcription language-understanding api-integration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

License

Apache-2.0

Last pushed

Nov 10, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/exemplaryai/ai-engine"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.