node-transcription and node-text-to-speech
These two tools are complements within the Deepgram ecosystem, as the transcription tool converts speech to text, which can then be used as input for the text-to-speech tool to generate spoken output.
About node-transcription
deepgram-starters/node-transcription
Get started using Deepgram's Transcription with this Node demo app
Implements real-time audio transcription through a full-stack architecture with a Node.js backend server and separate frontend application communicating via WebSocket or HTTP. Demonstrates Deepgram API integration with environment-based authentication and includes both browser-based and CLI setup workflows. Built with pnpm workspaces for monorepo management across backend and frontend components.
About node-text-to-speech
deepgram-starters/node-text-to-speech
Get started using Deepgram's Text-to-Speech with this Node demo app
Implements a full-stack demo with a Node.js backend server and frontend client communicating via API endpoints to synthesize speech from text input. The application uses Deepgram's TTS API with configurable settings and serves audio playback through a browser interface on localhost:8080, manageable through Makefile commands or manual server startup.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work