feat(speech): add prompt voice input (#249)

## Summary
- add server-backed speech capabilities and transcription endpoints plus
UI settings for speech configuration
- add push-to-talk prompt voice input with microphone controls,
transcription insertion, and browser capability gating
- keep prompt controls aligned by restoring right-side nav placement and
moving the mic beside the expand control
This commit is contained in:
Shantur Rathore
2026-03-25 14:08:11 +00:00
committed by GitHub
parent a950d47df0
commit 1233121a13
40 changed files with 1545 additions and 27 deletions

View File

@@ -7,6 +7,9 @@ import type {
FileSystemCreateFolderResponse,
FileSystemListResponse,
InstanceData,
SpeechCapabilitiesResponse,
SpeechSynthesisResponse,
SpeechTranscriptionResponse,
ServerMeta,
WorkspaceCreateRequest,
WorkspaceDescriptor,
@@ -235,6 +238,27 @@ export const serverApi = {
body: JSON.stringify({ path }),
})
},
fetchSpeechCapabilities(): Promise<SpeechCapabilitiesResponse> {
return request<SpeechCapabilitiesResponse>("/api/speech/capabilities")
},
transcribeAudio(payload: {
audioBase64: string
mimeType: string
filename?: string
language?: string
prompt?: string
}): Promise<SpeechTranscriptionResponse> {
return request<SpeechTranscriptionResponse>("/api/speech/transcribe", {
method: "POST",
body: JSON.stringify(payload),
})
},
synthesizeSpeech(payload: { text: string; format?: "mp3" | "wav" | "opus" }): Promise<SpeechSynthesisResponse> {
return request<SpeechSynthesisResponse>("/api/speech/synthesize", {
method: "POST",
body: JSON.stringify(payload),
})
},
listFileSystem(path?: string, options?: { includeFiles?: boolean }): Promise<FileSystemListResponse> {
const params = new URLSearchParams()
if (path && path !== ".") {