Skip to content

feat: support custom OpenAI-compatible whisper endpoints #65

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
toanbot wants to merge 2 commits into
base: main
Choose a base branch
from
+11 −3
Open

feat: support custom OpenAI-compatible whisper endpoints #65

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f3c2290
feat: support custom OpenAI-compatible whisper endpoints
toanbot Feb 3, 2026
bef693a
fix: add missing media extensions to isDirectMediaUrl
toanbot Feb 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion packages/core/src/content/url.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,7 +73,7 @@ export function extractYouTubeVideoId(rawUrl: string): string | null {
}

export function isDirectMediaUrl(url: string): boolean {
return /\.(mp4|mov|m4v|mkv|webm|mp3|m4a|wav|flac|aac)(\?|#|$)/i.test(url)
return /\.(mp4|mov|m4v|mkv|webm|mpeg|mpg|avi|wmv|flv|mp3|m4a|wav|flac|aac|ogg|opus|aiff|wma)(\?|#|$)/i.test(url)
}

export function shouldPreferUrlMode(url: string): boolean {
Expand Down
12 changes: 10 additions & 2 deletions packages/core/src/transcription/whisper/openai.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,8 @@ export async function transcribeWithOpenAi(
bytes: Uint8Array,
mediaType: string,
filename: string | null,
apiKey: string
apiKey: string,
baseUrl?: string | null
): Promise<string | null> {
const form = new FormData()
const providedName = filename?.trim() ? filename.trim() : 'media'
Expand All @@ -14,7 +15,14 @@ export async function transcribeWithOpenAi(
form.append('file', new Blob([toArrayBuffer(bytes)], { type: mediaType }), safeName)
form.append('model', 'whisper-1')

const response = await globalThis.fetch('https://api.openai.com/v1/audio/transcriptions', {
// Support custom OpenAI-compatible whisper endpoints via OPENAI_WHISPER_BASE_URL or OPENAI_BASE_URL
const effectiveBaseUrl = baseUrl
?? process.env.OPENAI_WHISPER_BASE_URL
?? process.env.OPENAI_BASE_URL
?? 'https://api.openai.com/v1'
const transcriptionUrl = `${effectiveBaseUrl.replace(/\/+$/, '')}/audio/transcriptions`

const response = await globalThis.fetch(transcriptionUrl, {
method: 'POST',
headers: { Authorization: `Bearer ${apiKey}` },
body: form,
Expand Down