JSPM

Found 98 results for asr

@deepgram/sdk

Isomorphic Javascript client for Deepgram

  • v4.11.2
  • 79.34
  • Published

@deepgram/captions

Node implementation of Deepgram's WebVTT and SRT formatting. Given a transcription, this package can return a valid string to store as WebVTT or SRT caption files.

  • v1.2.0
  • 75.70
  • Published

vosk-browser

Kaldi in-browser speech recognition based on a WASM build of the Vosk library

  • v0.0.8
  • 56.95
  • Published

react-native-vosk

Speech recognition module for react native using Vosk library

  • v2.1.6
  • 47.47
  • Published

sherpa-onnx-node

Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection

  • v1.12.14
  • 47.14
  • Published

sherpa-onnx

Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection

  • v1.12.14
  • 46.02
  • Published

@inworld/nodejs-sdk

The **Inworld AI Node.js SDK** enables Developers to easily integrate AI characters into your Node.js environment.

  • v1.17.0
  • 45.00
  • Published

sherpa-onnx-linux-x64

Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection

  • v1.12.14
  • 44.58
  • Published

sherpa-onnx-darwin-arm64

Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection

  • v1.12.14
  • 39.64
  • Published

sherpa-onnx-win-ia32

Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection

  • v1.12.14
  • 38.11
  • Published

sherpa-onnx-win-x64

Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection

  • v1.12.14
  • 37.99
  • Published

mmir-lib

MMIR (Mobile Multimodal Interaction and Relay) library

  • v7.1.0
  • 36.36
  • Published

sherpa-ncnn

Real-time speech recognition with Next-gen Kaldi

  • v2.1.12
  • 35.61
  • Published

sherpa-onnx-linux-arm64

Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection

  • v1.12.14
  • 34.31
  • Published

@inworld/runtime

The Inworld Runtime SDK is the first AI runtime built for consumer applications. Ship faster, automate operations, and experiment in real-time.

  • v0.6.3
  • 32.74
  • Published

@coze/realtime-api

A powerful real-time communication SDK for voice interactions with Coze AI bots | 扣子官方实时通信 SDK,用于与 Coze AI bots 进行语音交互

  • v1.3.2
  • 32.52
  • Published

sherpa-onnx-darwin-x64

Speech-to-text, text-to-speech, speaker diarization, and speech enhancement using Next-gen Kaldi without internet connection

  • v1.12.14
  • 31.33
  • Published

@flycut/caption-react

FlyCut Caption - AI-powered video subtitle editing React component with complete editing suite

  • v1.1.0
  • 28.50
  • Published

dwani

TypeScript SDK for the Dwani API, supporting Chat, Vision, ASR, TTS, Translation, and Documents

  • v0.0.4
  • 27.78
  • Published

@inworld/web-threejs

The Inworld Three.js library for the Web SDK. Includes Innequin, and Ready Player Me avatars ready to be used in a Three.js scene.

  • v1.6.0
  • 27.25
  • Published

@moonshine-ai/moonshine-js

On-device speech-to-text and voice control for web applications with Moonshine.

  • v0.1.29
  • 27.02
  • Published

n8n-nodes-transcribe-audio

Perform speech-to-text on audio files within your n8n workflows.This node provides local audio transcription, no internet or third-party APIs required for processing.

  • v0.1.23
  • 26.74
  • Published

asr-sdk-dev

JavaScript SDK for Cariva ASR

    • v1.6.10
    • 25.83
    • Published

    @fly-cut/caption-react

    FlyCut Caption - AI-powered video subtitle editing React component with complete editing suite

    • v1.0.0
    • 24.72
    • Published

    @cariva/asr-sdk

    JavaScript SDK for Cariva ASR

      • v1.6.3
      • 24.49
      • Published

      xfyun-sdk

      科大讯飞语音识别 SDK,支持浏览器中实时语音听写功能

      • v1.0.2
      • 24.12
      • Published

      @asr_sdk/wx

      爱收入微信SDK

      • v0.0.10
      • 23.53
      • Published

      @usefulsensors/moonshine-js

      On-device speech-to-text and voice control for web applications with Moonshine.

      • v0.1.21
      • 20.53
      • Published

      voice2text

      speech to text functionality with minimum configuration and maximum compatibility

      • v0.5.6
      • 20.44
      • Published

      asr-sdk-qa

      JavaScript SDK for Cariva ASR

        • v1.5.6
        • 19.80
        • Published

        yandex-speech

        node.js module for Yandex speech systems (ASR & TTS)

        • v0.0.14
        • 19.49
        • Published

        vosk-wasm

        WebAssembly build of the Vosk library

        • v0.0.1
        • 19.49
        • Published

        mmir-plugin-lang-support

        tools for querying supported languages (ASR and TTS) and voices (TTS) for mmir speech plugins

        • v1.5.0
        • 19.25
        • Published

        pray-calc

        Accurate prayer times using custom algorithm for dynamic angles and nrel-spa for extreme precision

        • v1.7.2
        • 18.65
        • Published

        mmir-plugin-speech-nuance-lang

        tools for querying supported languages (ASR and TTS) and voices (TTS) by Nuance / Cerence SpeechKit

        • v1.1.1
        • 18.04
        • Published

        @xmov/doubao-asr

        豆包(字节跳动)实时语音识别 SDK

        • v1.0.2
        • 16.98
        • Published

        adhan-clock

        adhan-clock is a prayer times calculation library for Muslims

        • v1.1.1
        • 16.54
        • Published

        whisper-nodejs-wrapper

        Node.js wrapper for OpenAI Whisper speech recognition with TypeScript support

        • v1.0.0
        • 16.39
        • Published

        @fciannella/nvidia-asr-client

        Minimal cross-platform wrapper around NVIDIA/Riva streaming ASR WebSocket API with optional client-side silence detection.

          • v0.1.9
          • 15.54
          • Published

          abenasdk

          Enterprise Node.js SDK for Abena AI Services - ASR, TTS, Translation

          • v0.1.1
          • 15.05
          • Published

          mmir-plugin-speech-io

          Plugin for the MMIR framework that adds state-machines for managing speech input/output states

          • v2.0.3
          • 14.30
          • Published

          infobot-sber-stt

          Node.JS library for Sber SmartSpeech Speech-to-Text with streaming recognition

          • v1.1.4
          • 14.03
          • Published

          salat-times-calculator

          Professional Islamic prayer times calculator with multiple calculation methods, adjustments, and caching. Used in Salat Now app by Anis Mosbah.

          • v1.0.0
          • 13.60
          • Published

          funasr-client

          Really easy-to-use Typescript client for FunASR runtime server.

          • v0.1.2
          • 13.46
          • Published

          adaptive-speech-recognizer

          Adaptive dictation-mode speech recognizer ponyfill compatible with WebChat that gives the user time to think and stutter/stammer.

          • v2.2.0
          • 13.33
          • Published

          salat-first

          Islamic prayer times calculation with special support for Moroccan methods and Maliki madhab

            • v1.0.4
            • 12.96
            • Published

            infobot-yandex-stt

            Node.JS library for Yandex Cloud Speech-to-Text with streaming recognition

            • v1.1.3
            • 12.79
            • Published

            pcm-s16le-recorder

            Pure browser PCM S16LE audio recorder via AudioWorklet for ASR (no MediaRecorder, no Opus).

            • v1.0.1
            • 11.47
            • Published

            @koi-rtc/speech-sdk

            统一的语音服务SDK,支持多个云服务商的ASR和TTS服务

              • v1.0.3
              • 11.21
              • Published

              vosk-browserli

              Fork of ccoreilly's vosk-browser to enable mbr vectors on partial results. Praise kaldi

              • v0.0.9
              • 10.71
              • Published

              transcription-lib-grpc-js

              Creates Live Transcription of a media input stream in multiple languages

              • v1.0.2
              • 10.44
              • Published

              dowow-web-threejs

              The Inworld Three.js library for the Web SDK. Includes Innequin, and Ready Player Me avatars ready to be used in a Three.js scene.

              • v1.1.1
              • 9.11
              • Published

              n8n-nodes-asr

              N8N node for processing audio files via an ASR service

              • v0.1.1
              • 8.80
              • Published

              infobot-tinkoff-stt

              Node.JS library for Tinkoff VoiceKit Speech-to-Text with streaming recognition

              • v1.1.0
              • 8.64
              • Published

              asr-scroll-position

              Manually update the browser's scroll position when using pushState routing with abstract-state-router

              • v1.1.0
              • 7.95
              • Published

              @texttree/voice2text

              (fork of @m-abdi/voice2text)speech to text functionality with minimum configuration and maximum compatibility

              • v0.5.2
              • 7.80
              • Published

              koishi-plugin-whisper-asr

              [openai whisper-asr](https://github.com/ahmetoner/whisper-asr-webservice) 语音识别服务,支持一百多种语言+翻译,适配wechaty语音消息

              • v1.0.4
              • 6.73
              • Published

              asr-vietspeech

              Asr Vietspech library for convert audio to text with Vietnamese language.

              • v1.0.17
              • 2.58
              • Published

              vosk-stt

              Node.js bindings for Vosk speech recognition

              • v1.0.0
              • 2.57
              • Published

              deepgram-next15-fix

              Isomorphic Javascript client for Deepgram

              • v0.0.0-automated
              • 0.00
              • Published