JSPM

Found 200 results for transcription

gladia

Official TypeScript SDK for Gladia - State-of-the-art Speech to Text API

  • v0.1.3
  • 12.07
  • Published

transcription

Documentation generator for ES6.

  • v0.2.1
  • 11.89
  • Published

podcast-takeaways

A system to download the most recent episode of a plugin, transcribe it with the OpenAI Whisper API and then use GPT to determine one takeaway to apply from the episode.

    • v0.4.5
    • 11.14
    • Published

    kana-transformer

    Transform kana to en|ru language or vice versa, using specific transliteration system; convert one kana to the other syllabary

    • v3.5.0
    • 11.10
    • Published

    transcription-lib-grpc-js

    Creates Live Transcription of a media input stream in multiple languages

    • v1.0.2
    • 10.97
    • Published

    pronunciation-finder

    An application for getting audio files with pronunciation from public dictionaries

    • v0.8.0
    • 10.94
    • Published

    cmu-pronouncing-dictionary-cjs

    Common JS version of the 134,000+ words and their pronunciations in the CMU pronouncing dictionary

    • v3.0.0
    • 10.94
    • Published

    twitter-reply

    Strange Text Transliterator (GOTO: spongescribe)

    • v0.0.0
    • 10.56
    • Published

    transcription-words

    Easy and crystal-clear API for transcription words.

    • v1.2.1
    • 10.21
    • Published

    video-summary

    Video Summary SDK is a powerful Node.js module for advanced video processing, offering features like speech-to-text transcription, content summarization, automatic chapter extraction, and comprehensive video summarization. It's perfect for developers look

    • v1.0.8
    • 9.62
    • Published

    polyanno_storage

    Node and Express backend for easy MongoDB storage of Polyanno annotations

    • v0.1.5
    • 9.61
    • Published

    twitter-search-bot

    Strange Text Transliterator (GOTO: spongescribe)

    • v0.0.0
    • 9.61
    • Published

    @speechall/sdk

    TypeScript SDK for the Speechall API - A powerful and flexible speech-to-text service

    • v1.0.0
    • 9.55
    • Published

    @voxextractlabs/vox-whisper

    [![NPM](https://img.shields.io/npm/v/@voxextractlabs/vox-whisper?label=npm)](https://www.npmjs.com/package/@voxextractlabs/vox-whisper) [![License](https://img.shields.io/npm/l/@voxextractlabs/vox-whisper)](./LICENSE) [![Build Status](https://github.com/V

    • v1.0.1
    • 9.05
    • Published

    node-palladius

    The Palladius system for transcribing Chinese characters into the Cyrillic alphabet

    • v0.6.4
    • 8.49
    • Published

    image-generation

    Strange Text Transliterator (GOTO: spongescribe)

    • v0.0.0
    • 8.46
    • Published

    transcord

    A simple recording and transcription module.

    • v0.2.0
    • 8.30
    • Published

    voicely

    Voicely - A CLI tool to transcribe audio files and summarize the transcriptions using OpenAI's APIs.

    • v1.1.5
    • 7.93
    • Published

    audio-transcripter

    Lightweight TypeScript library for transcribing audio files using Google Gemini 2.0 models. Supports local files, remote URLs, and Blobs.

    • v2.0.1
    • 7.82
    • Published

    atc-transcription

    React Native module for transcribing WAV files using WhisperKit

      • v1.0.0
      • 7.82
      • Published

      react-transcribe

      React component for speech-to-text transcription with silence detection

      • v0.1.0
      • 7.82
      • Published

      @rxtk/stt-gcp

      👂 RxJS operator for realtime speech-to-text (STT/S2T) using Google speeh-to-text

      • v0.0.0
      • 7.80
      • Published

      liblouis-js

      javascript bindings for liblouis

      • v0.2.0
      • 7.50
      • Published

      spongescribebot

      Strangetext Transcription - Use: 'spongescribe'

      • v0.0.0
      • 7.16
      • Published

      maketalk

      A command-line tool to create video presentations with title cards and transcriptions

        • v1.4.0
        • 7.16
        • Published

        glaemscribe

        Glǽmscribe (also written Glaemscribe) is a software dedicated to the transcription of texts between writing systems, and more specifically dedicated to the transcription of J.R.R. Tolkien's invented languages to some of his devised writing systems.

        • v1.3.1
        • 7.07
        • Published

        nwhisper

        Native Node.js bindings for OpenAI's Whisper using whisper.cpp. High-performance local speech-to-text with custom model support.

        • v0.3.0
        • 7.06
        • Published

        meeting-whisperer

        CLI tool that transcribes audio/video files using AssemblyAI's API and outputs formatted markdown transcripts

          • v0.1.0
          • 7.06
          • Published

          node-deepgram

          Node wrapper for Deepgram

          • v1.0.10
          • 7.04
          • Published

          karaoke-transcriber

          A CLI tool to generate karaoke-style subtitles on videos using Whisper and FFmpeg.

            • v1.0.3
            • 7.04
            • Published

            multi-voice-sdk

            A universal Text-to-Speech (TTS) and Speech-to-Text (STT) SDK supporting multiple providers (OpenAI, Google Gemini, Deepgram, Groq PlayAI, Cartesia, AssemblyAI) with audio merging capabilities

              • v1.1.0
              • 6.52
              • Published

              vidscript

              AI-powered CLI tool that transforms video content into intelligent, structured notes and scripts

              • v1.0.6
              • 6.19
              • Published

              noapi-speech2text

              Speech recognition library that uses web-based services to convert speech to text in multiple languages

              • v1.0.3
              • 5.24
              • Published

              @rxtk/stt-aws

              👂 RxJS operator for realtime speech-to-text (STT/S2T) using AWS Transcribe

              • v0.0.0
              • 5.17
              • Published

              realtime-stt-client

              TypeScript client library for Realtime Speech-to-Text server

                • v0.0.1-poc.6
                • 5.17
                • Published

                friendlyjs

                make friendly URLs by stripping out non lating chars, and convert other chars to their latin counterparts

                • v0.0.1
                • 5.15
                • Published

                voicekey

                A CLI tool to transcribe voice to text with interactive UI

                • v1.0.0
                • 5.15
                • Published

                speak-precisely-sdk

                Real-time speech transcription and translation SDK

                • v1.0.1
                • 5.15
                • Published

                ai-meeting-summarizer

                A simple Node.js library to transcribe and summarize meeting recordings using OpenAI's GPT model and Whisper.

                  • v1.0.1
                  • 5.15
                  • Published

                  dnable

                  Simple, lightweight, and fast Node.js module for enabling DNA sequences.

                    • v0.2.1
                    • 4.31
                    • Published

                    fireflies

                    Fireflies.ai API wrapper

                    • v0.0.1
                    • 4.11
                    • Published

                    speechtotext-openaikey

                    A React component for recording and transcribing audio using the Web Audio API and OpenAI.

                      • v1.0.2
                      • 3.96
                      • Published

                      alinkeo-core

                      This is the official alinkeo core npm package

                      • v1.0.0
                      • 3.90
                      • Published

                      @lunarisapp/cmudict

                      A JavaScript interface to the CMU Pronouncing Dictionary

                      • v1.0.0
                      • 3.90
                      • Published

                      n8n-nodes-asr

                      N8N node for processing audio files via an ASR service

                      • v0.1.1
                      • 3.90
                      • Published

                      douyin-text-extractor

                      Node.js + TypeScript library for extracting text from Douyin/TikTok videos

                      • v1.1.2
                      • 2.41
                      • Published

                      rev_ai

                      Unofficial Rev AI Node.js client

                      • v0.5.1
                      • 2.32
                      • Published

                      lucidtalk-core

                      Privacy-first P2P meeting transcription and AI SDK

                      • v1.0.0
                      • 2.32
                      • Published

                      subtitles-editor

                      A React component for editing SRT and VTT subtitles directly in a textarea, styled with TailwindCSS.

                      • v0.0.1
                      • 2.29
                      • Published

                      whisper-stream-js

                      CLI tool for real-time audio transcription using OpenAI's Whisper API

                      • v1.0.0
                      • 2.29
                      • Published

                      meeshx-sdk

                      Welcome to MeeshX! Choose your favorite provider and transcribe your audio content in less than 5 minutes.

                        • v1.0.0
                        • 2.28
                        • Published

                        whisper-clipboard-cli

                        Own your transcription workflow. Press Cmd+Shift+X, speak, get text in clipboard instantly.

                          • v1.0.0
                          • 0.00
                          • Published

                          ctrl.so

                          Embedable vocal intelligence

                          • v0.0.8
                          • 0.00
                          • Published

                          openwhisper

                          A library for AI-powered audio transcription with local and remote server fallback.

                            • v1.0.1
                            • 0.00
                            • Published

                            deepgram-media-transcriber

                            A package to transcribe media files using Deepgram with speaker-labeled subtitles (SRT/VTT).

                              • v1.0.8
                              • 0.00
                              • Published

                              edit-wave-transcript

                              react component for transcription with ability to edit the words as well as the words. synchronization is done between words and wave-forms.

                              • v0.2.0
                              • 0.00
                              • Published

                              @easyscribe/react

                              React components for transcribing with easyscribe.org

                              • v1.0.1
                              • 0.00
                              • Published

                              amoeba-life-cycle

                              A simple module that simulates the life cycle of an amoeba at the molecular level by using a (semi) TRNG.

                              • v1.0.0
                              • 0.00
                              • Published

                              tafrigh-cli

                              CLI for using the tafrigh library.

                                • v1.4.2
                                • 0.00
                                • Published

                                @lunarity/a2s-cli

                                A CLI tool for transcribing audio files to subtitles

                                • v1.0.3
                                • 0.00
                                • Published