Files
openchamber/packages/web/server/lib/tts/stt.js
T
yangyaofeiandBohdan Triapitsyn 06526767a2 feat(tts/stt): add API key support for OpenAI-compatible custom providers (#1361)
* feat(tts/stt): add API key support for OpenAI-compatible custom providers

## Problem
Custom (OpenAI-compatible) TTS/STT provider in Voice Settings has no way to
pass an API key or bearer token. Many self-hosted or third-party compatible
servers require authentication, making them unreachable from OpenChamber.

The server-side TTS route already accepts an `apiKey` parameter, but the
frontend never sends it. The STT route hardcodes `'not-required'`.

## Implementation
- Add `openaiCompatibleApiKey` to Zustand config store, persisted to localStorage
- Add API Key input field in VoiceSettings.tsx under the custom provider section
- Wire `openaiCompatibleApiKey` through useServerTTS to the TTS backend
- Add `apiKey` field to AudioStreamConfig for STT, forwarded as X-API-Key header
- Update server STT route to accept and forward X-API-Key to transcribeAudio
- Update stt.js to use client-provided apiKey before falling back to env var

## Files changed
- packages/ui/src/stores/useConfigStore.ts
- packages/ui/src/components/sections/openchamber/VoiceSettings.tsx
- packages/ui/src/hooks/useServerTTS.ts
- packages/ui/src/hooks/useBrowserVoice.ts
- packages/ui/src/lib/voice/audioStreamService.ts
- packages/web/server/lib/tts/routes.js
- packages/web/server/lib/tts/stt.js

* feat(tts/stt): add separate API key support for custom TTS and STT providers

## Problem
Custom (OpenAI-compatible) TTS and STT providers in Voice Settings have no way
to pass API keys. Many self-hosted or third-party compatible servers require
authentication, making them unreachable from OpenChamber Desktop (Electron).

## Implementation
- Add `openaiCompatibleApiKey` for TTS (persisted to localStorage, passed in JSON body)
- Add `sttApiKey` for STT (persisted to localStorage, passed via Authorization: Bearer header)
- Two independent keys: TTS and STT are configured separately
- STT authentication follows OpenAI standard (Authorization: Bearer <token>)
- TTS authentication follows existing pattern (apiKey in JSON body)
- Backend STT route extracts bearer token from Authorization header
- Backend STT service prefers client-provided key over OPENAI_API_KEY env var

## Fixes
- Fixed P1: ConfigStore interface now declares setOpenaiCompatibleApiKey setter
- STT API key is only forwarded when sttProvider === 'server' (not leaked to other providers)

## Files changed (7)
- packages/ui/src/stores/useConfigStore.ts
- packages/ui/src/components/sections/openchamber/VoiceSettings.tsx
- packages/ui/src/hooks/useServerTTS.ts
- packages/ui/src/hooks/useBrowserVoice.ts
- packages/ui/src/lib/voice/audioStreamService.ts
- packages/web/server/lib/tts/routes.js
- packages/web/server/lib/tts/stt.js

* fix: refresh server STT callback when API key changes

---------

Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
2026-05-24 00:58:22 +03:00

77 lines
2.4 KiB
JavaScript

/**
* Server-side Speech-to-Text Service
*
* Proxies audio to any OpenAI-compatible transcription endpoint
* (e.g. faster-whisper, whisper.cpp) using the OpenAI Node SDK.
*/
import OpenAI, { toFile } from 'openai';
import { normalizeCustomOpenAIBaseURL } from './base-url.js';
/**
* Transcribe an audio buffer via an OpenAI-compatible /v1/audio/transcriptions endpoint.
*
* @param {object} opts
* @param {Buffer} opts.audioBuffer - Raw audio bytes
* @param {string} opts.mimeType - MIME type of the audio (e.g. 'audio/webm')
* @param {string} opts.model - Model name accepted by the remote server
* @param {string} [opts.baseURL] - Base URL of the compatible server (including /v1)
* @param {string} [opts.apiKey] - Optional API key for the compatible server
* @param {string} [opts.language] - Optional BCP-47 language hint (e.g. 'en')
* @returns {Promise<string>} Transcribed text
*/
export async function transcribeAudio({ audioBuffer, mimeType, model, baseURL, apiKey, language }) {
const normalizedBaseURLResult = normalizeCustomOpenAIBaseURL(baseURL);
if (normalizedBaseURLResult.error) {
throw new Error(normalizedBaseURLResult.error);
}
const normalizedBaseURL = normalizedBaseURLResult.value;
if (!normalizedBaseURL) {
throw new Error('Custom server URL is required');
}
const clientOpts = {
apiKey: apiKey || process.env.OPENAI_API_KEY || 'not-required',
};
clientOpts.baseURL = normalizedBaseURL;
const client = new OpenAI(clientOpts);
// Derive a sensible filename extension from the MIME type so the server
// can infer the codec when it isn't explicit in the stream header.
const ext = mimeTypeToExt(mimeType);
const filename = `audio.${ext}`;
const file = await toFile(audioBuffer, filename, { type: mimeType });
const result = await client.audio.transcriptions.create({
file,
model,
response_format: 'json',
...(language ? { language } : {}),
});
return result.text ?? '';
}
/**
* Map a MIME type to a file extension understood by Whisper servers.
* @param {string} mimeType
* @returns {string}
*/
function mimeTypeToExt(mimeType) {
const type = (mimeType || '').split(';')[0].trim().toLowerCase();
const map = {
'audio/webm': 'webm',
'audio/ogg': 'ogg',
'audio/wav': 'wav',
'audio/wave': 'wav',
'audio/mpeg': 'mp3',
'audio/mp4': 'mp4',
'audio/mp3': 'mp3',
'audio/flac': 'flac',
};
return map[type] ?? 'webm';
}