GitHub Preview Coding by Voice Feature for AI Programming Assistant Copilot
GitHub is adding voice control to its coding through the Copilot AI programming assistant, the company announced at its GitHub Universe conference. The virtual coding aide will add “Hey, GitHub” as a wake word and enable developers to write, search through, and summarize code segments through speech.
GitHub Copilot is an AI “pair programmer” that debuted in June after a year in technical previews. It performs as the junior partner to a developer, offering ideas, spotting errors, and generally improving coding projects. Copilot is descended from the specialized Codex form of OpenAI’s GPT-3 language model and adapts to a programmer’s style so as to improve the suggestions it offers. Github Copilot costs $10 a month or $100 a year and offers a 60-day free trial.
The new voice service expands that collaboration to voice by adding “Hey, GitHub” as a wake word and accepting commands for things to add and edit in the code. It can suggest code, summarize what certain sections do, and navigate through the code, moving the cursor to specific lines, though it won’t respond vocally as of now. The feature is currently undergoing testing with the GitHub Next research team but eventually could speed up programming because voice is faster than using a mouse and keyboard. It would also make coding more accessible to those who can’t use the standard manual tools.
“AI will soon be integrated into every aspect of the developer experience, and, therefore, we’re making GitHub Copilot even more accessible,” Github CEO Thomas Dohmke explained in a blog post. “With the power of your voice, we’re excited about the potential to bring the benefits of GitHub Copilot to even more developers, including developers who have difficulty typing using their hands. “Hey, GitHub!” only reduces the need for a keyboard when coding within VS Code for now, but we hope to expand its capabilities through further research and testing.”
Generative AI can be enormously beneficial for programming, as evidenced by a recent survey of more than 2,000 programmers finding that Copilot users are likely to code faster and feel “more fulfilled with their job” Nearly three-quarters said Copilot enabled them to “focus on more satisfying work,” because the AI helped dispatch the more tedious and repetitive elements of coding. The voice connection will likely improve those numbers, especially for those who may prefer talking through their code without typing.
Follow @voicebotaiFollow @erichschwartz
GitHub’s Copilot AI Coding Assistant Boosts Developer Productivity and Happiness: Report
OpenAI Releases Open-Source ‘Whisper’ Transcription and Translation AI