Files
Tyler Slaton 7673b8dfb8 fix(build): load tsdown exports helper as .mjs under native config loader
CI build runners use a Node with native TypeScript stripping enabled
(process.features.typescript), so tsdown selects its native ESM config
loader. That loader cannot resolve the extensionless relative import
"../../scripts/tsdown-exports" in each tsdown.config.ts, so every package
build failed with "Cannot find module" — cascading into the unit, runtime,
and all integration jobs (which run the build first). Local builds used
tsdown's bundler loader instead, which is why this passed pre-push.

Ship the shared helper as scripts/tsdown-exports.mjs (real ESM) plus a
hand-written tsdown-exports.d.mts, imported with the explicit .mjs
extension. This resolves under the native loader, tsdown's bundler loader,
and tsc alike. The generated exports are unchanged — package.json maps stay
identical.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-09 20:39:07 -07:00
..
2026-04-10 23:38:59 +00:00

@copilotkit/voice

Audio transcription providers for CopilotKit.

Setup

pnpm add @copilotkit/voice openai
import { CopilotRuntime, createCopilotEndpoint } from "@copilotkit/runtime";
import { TranscriptionServiceOpenAI } from "@copilotkit/voice";
import OpenAI from "openai";

const runtime = new CopilotRuntime({
  agents: { default: yourAgent },
  transcriptionService: new TranscriptionServiceOpenAI({
    openai: new OpenAI({ apiKey: process.env.OPENAI_API_KEY }),
  }),
});

Once configured, the chat UI shows a microphone button. Users can record audio, which gets transcribed and inserted into the input field as text.

TranscriptionServiceOpenAI

Uses OpenAI Whisper for transcription.

new TranscriptionServiceOpenAI({
  openai: new OpenAI({ apiKey: "..." }), // required
  model: "whisper-1", // default
  language: "en", // optional, ISO-639-1 code
  prompt: "Technical discussion context", // optional, helps with domain terms
  temperature: 0, // optional, 0 = deterministic
});

Custom providers

Extend TranscriptionService from runtime:

import {
  TranscriptionService,
  TranscribeFileOptions,
} from "@copilotkit/runtime";

class MyTranscriptionService extends TranscriptionService {
  async transcribeFile(options: TranscribeFileOptions): Promise<string> {
    // options.audioFile, options.mimeType, options.size
    return "transcribed text";
  }
}