Search results
29 packages found
Node.js bindings for OpenAI's Whisper. Runs local on CPU.
- OpenAI
- Whisper
- CPP
- C++
- Bindings
- Transcribe
- Transcriber
- Transcript
- Transcription
- Audio
- Speech
- Speech-to-Text
- STT
- TTS
- View more
convert an AWS transcribe JSON body into a .vtt file
Node.js plugin for speech recognition that works with OpenAI's Whisper models using ONNX.
- openai
- whisper
- onnx
- huggingface
- transformers
- transformers.js
- transcribe
- audio recognition
- speech
- speech-to-Text
- wav2text
- stt
- tts
Convert AWS transcription JSON to srt
Transcribe from text tracks
Turn JSON from Amazon AWS Transcribe into VTT files for use as subtitles.
Node.js client library for Soniox speech recognition service.
A package to test if your media file is supported for transcription.
This node module aims to get as an input a link to youtube video and return as an output its transcribtion in a JSON format.
Generates a copy of all or part of a JSON object, renaming keys and/or otherwise transforming the object in the process.
Transposer connector is a PeerTube language tool plugin to transcribe and translate with Whisper
Speech-to-Text as easy as it goes
A custom vocabulary that you can use to change the way Amazon Transcribe handles transcription of an audio file.
- cdk
- awscdk
- aws-cdk
- cloudformation
- cfn
- extensions
- constructs
- cfn-resources
- cloudformation-registry
- l1
- generic
- transcribe
- vocabulary
Convert Transcribe! v7 .xsc files (which contain annotations of music) to a readable JSON format
A command-line utility to generate transcripts from a Discord channel
Polyfill for the SpeechRecognition browser API using AWS Transcribe
Transcribe audio of any length using Google's Speech to Text API
Intelloid Web STT Example test Open a terminal session at the parent directory "real-time-example" Run npm i to ensure all needed modules are installed Add your Token to line 13 in ./js/server.js Spin up the server to get your temporary auth token us
Tool for aligning Chinese transcripts with audio using the AWS transcribe service