feat(voice): add voice input/output support with multiple providers (#281)
* feat(voice): add voice input/output support with multiple providers - Add BrowserVoiceButton component for Web Speech API voice input - Add VoiceProvider context for managing voice state across the app - Add TTS (Text-to-Speech) support with browser, macOS Say, and OpenAI providers - Add message TTS buttons to read assistant messages aloud - Add VoiceSettings page in OpenChamber settings - Add server endpoints for TTS and summarization services - Include slider component for voice rate/pitch/volume controls - Add hidden session support for background voice operations - Add Caddyfile for HTTPS support (required for microphone access) * fix: Build errors fixed and removed outdated ElevenLabs test code. * refactor(voice): use zen API with gpt-5-nano for TTS summarization Replace the hidden session + OpenCode SDK approach with direct calls to the opencode.ai zen API (same pattern used for commit message and PR description generation). - Rewrite summarization-service.js to call zen/v1/responses with gpt-5-nano - Remove hidden session logic (hiddenSession.ts, sessionStore filtering) - Remove summarizeModel setting and model selector from VoiceSettings - Simplify client-side summarize.ts to no longer pass model params - Clean up callers in useMessageTTS and useBrowserVoice * fix(voice): remove false 'voice not supported' warning in settings Mobile Safari does support voice but the isSupported check was incorrectly flagging it. Remove the warning banner entirely. * feat(voice): add configurable summary length limit for TTS output Add a slider (50-2000 chars) in voice settings to control max summary length. The limit is passed through the summarize endpoint and speak endpoint to the zen API prompt, with token budget scaled accordingly. * fix(voice): add diagnostic logging and sanitize TTS fallback Add console logging throughout the summarization flow (client + server) to trace why text may not be summarized. Fix silent error swallowing in /api/tts/speak. Always apply sanitizeForTTS even when summarization is disabled so raw markdown/code is never spoken verbatim. * fix(voice): fix token budget starving model of output tokens max_output_tokens includes both reasoning and output tokens. With effort:'low', reasoning alone consumes ~128 tokens, so a budget of 100 left zero tokens for the actual summary text. Use a fixed 1000 token budget (matching commit message generation) and control output length via the prompt's character limit instruction instead. * chore(voice): remove diagnostic logging from summarization flow * fix(voice): don't request mic permission on mobile page load Remove the useEffect that pre-requested microphone permission when the BrowserVoiceButton component mounted on mobile. This caused an unwanted permission prompt immediately on page load before the user tapped the mic icon. Permission is now only requested on explicit user interaction. * fix(voice): remove unused BrowserVoiceButton binding * fix(voice): desktop mic flow + non-continuous draft mode * fix(voice): stabilize continuous loop and polish controls * feat(settings): mark voice section experimental --------- Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>
This commit is contained in:
gsxdsm
committed by
GitHub
GitHub
co-authored by
Bohdan Triapitsyn
Bohdan Triapitsyn
parent
6776ac31c2
commit
1ed5316ac7
@@ -8,6 +8,7 @@ import {
|
||||
RiFileUploadLine,
|
||||
RiSendPlane2Line,
|
||||
} from '@remixicon/react';
|
||||
import { BrowserVoiceButton } from '@/components/voice';
|
||||
import { useSessionStore } from '@/stores/useSessionStore';
|
||||
import { useConfigStore } from '@/stores/useConfigStore';
|
||||
import { useUIStore } from '@/stores/useUIStore';
|
||||
@@ -1438,6 +1439,7 @@ export const ChatInput: React.FC<ChatInputProps> = ({ onOpenSettings, scrollToBo
|
||||
const iconSizeClass = isMobile ? 'h-[18px] w-[18px]' : (isVSCode ? 'h-4 w-4' : 'h-[18px] w-[18px]');
|
||||
|
||||
const iconButtonBaseClass = 'flex items-center justify-center text-muted-foreground transition-none outline-none focus:outline-none flex-shrink-0';
|
||||
const footerIconButtonClass = cn(iconButtonBaseClass, buttonSizeClass);
|
||||
|
||||
// Send button - respects queue mode setting
|
||||
const sendButton = (
|
||||
@@ -1472,8 +1474,7 @@ export const ChatInput: React.FC<ChatInputProps> = ({ onOpenSettings, scrollToBo
|
||||
handlePrimaryAction();
|
||||
}}
|
||||
className={cn(
|
||||
iconButtonBaseClass,
|
||||
buttonSizeClass,
|
||||
footerIconButtonClass,
|
||||
canSend && (currentSessionId || newSessionDraftOpen)
|
||||
? 'text-primary hover:text-primary'
|
||||
: 'opacity-30'
|
||||
@@ -1514,8 +1515,7 @@ export const ChatInput: React.FC<ChatInputProps> = ({ onOpenSettings, scrollToBo
|
||||
handleQueueMessage();
|
||||
}}
|
||||
className={cn(
|
||||
iconButtonBaseClass,
|
||||
buttonSizeClass,
|
||||
footerIconButtonClass,
|
||||
'absolute bottom-full left-1/2 -translate-x-1/2 mb-1',
|
||||
hasContent && currentSessionId
|
||||
? 'text-primary hover:text-primary'
|
||||
@@ -1533,8 +1533,7 @@ export const ChatInput: React.FC<ChatInputProps> = ({ onOpenSettings, scrollToBo
|
||||
type="button"
|
||||
onClick={handleAbort}
|
||||
className={cn(
|
||||
iconButtonBaseClass,
|
||||
buttonSizeClass,
|
||||
footerIconButtonClass,
|
||||
'text-[var(--status-error)] hover:text-[var(--status-error)]'
|
||||
)}
|
||||
aria-label="Stop generating"
|
||||
@@ -1586,7 +1585,7 @@ export const ChatInput: React.FC<ChatInputProps> = ({ onOpenSettings, scrollToBo
|
||||
<DropdownMenuTrigger asChild>
|
||||
<button
|
||||
type="button"
|
||||
className={cn(iconButtonBaseClass, isMobile && 'h-7 w-7')}
|
||||
className={footerIconButtonClass}
|
||||
title="Add attachment"
|
||||
aria-label="Add attachment"
|
||||
>
|
||||
@@ -1622,7 +1621,7 @@ export const ChatInput: React.FC<ChatInputProps> = ({ onOpenSettings, scrollToBo
|
||||
<button
|
||||
type='button'
|
||||
onClick={onOpenSettings}
|
||||
className={cn(iconButtonBaseClass, isMobile && 'h-7 w-7')}
|
||||
className={footerIconButtonClass}
|
||||
title='Model and agent settings'
|
||||
aria-label='Model and agent settings'
|
||||
>
|
||||
@@ -1631,13 +1630,13 @@ export const ChatInput: React.FC<ChatInputProps> = ({ onOpenSettings, scrollToBo
|
||||
) : null;
|
||||
|
||||
const attachmentsControls = (
|
||||
<div className="flex items-center gap-x-1">
|
||||
<div className="flex items-center gap-x-1.5">
|
||||
{isMobile ? (
|
||||
<button
|
||||
type="button"
|
||||
className={cn(
|
||||
iconButtonBaseClass,
|
||||
'h-7 w-7 rounded-md text-muted-foreground',
|
||||
footerIconButtonClass,
|
||||
'rounded-md text-muted-foreground',
|
||||
'hover:bg-interactive-hover/40 hover:text-foreground'
|
||||
)}
|
||||
onPointerDownCapture={(event) => {
|
||||
@@ -1873,6 +1872,7 @@ export const ChatInput: React.FC<ChatInputProps> = ({ onOpenSettings, scrollToBo
|
||||
<MobileAgentButton onCycleAgent={handleCycleAgent} onOpenAgentPanel={() => setMobileControlsPanel('agent')} className="min-w-0 flex-shrink" />
|
||||
</div>
|
||||
<div className="flex items-center gap-x-1 flex-shrink-0">
|
||||
<BrowserVoiceButton />
|
||||
{actionButtons}
|
||||
</div>
|
||||
</div>
|
||||
@@ -1898,6 +1898,7 @@ export const ChatInput: React.FC<ChatInputProps> = ({ onOpenSettings, scrollToBo
|
||||
</div>
|
||||
<div className={cn('flex items-center flex-1 justify-end', footerGapClass, 'md:gap-x-3')}>
|
||||
<ModelControls className={cn('flex-1 min-w-0 justify-end')} />
|
||||
<BrowserVoiceButton />
|
||||
{actionButtons}
|
||||
</div>
|
||||
</>
|
||||
|
||||
@@ -14,7 +14,7 @@ import { isEmptyTextPart, extractTextContent } from './partUtils';
|
||||
import { FadeInOnReveal } from './FadeInOnReveal';
|
||||
import { Button } from '@/components/ui/button';
|
||||
import { Tooltip, TooltipContent, TooltipTrigger } from '@/components/ui/tooltip';
|
||||
import { RiCheckLine, RiFileCopyLine, RiChatNewLine, RiArrowGoBackLine, RiGitBranchLine, RiHourglassLine } from '@remixicon/react';
|
||||
import { RiCheckLine, RiFileCopyLine, RiChatNewLine, RiArrowGoBackLine, RiGitBranchLine, RiHourglassLine, RiVolumeUpLine, RiStopLine } from '@remixicon/react';
|
||||
import { ArrowsMerge } from '@/components/icons/ArrowsMerge';
|
||||
import type { ContentChangeReason } from '@/hooks/useChatScrollManager';
|
||||
|
||||
@@ -24,6 +24,8 @@ import { useSessionStore } from '@/stores/useSessionStore';
|
||||
import { useUIStore } from '@/stores/useUIStore';
|
||||
import { flattenAssistantTextParts } from '@/lib/messages/messageText';
|
||||
import { MULTIRUN_EXECUTION_FORK_PROMPT_META_TEXT } from '@/lib/messages/executionMeta';
|
||||
import { useMessageTTS } from '@/hooks/useMessageTTS';
|
||||
import { useConfigStore } from '@/stores/useConfigStore';
|
||||
import { TextSelectionMenu } from './TextSelectionMenu';
|
||||
|
||||
const formatTurnDuration = (durationMs: number): string => {
|
||||
@@ -317,6 +319,19 @@ const AssistantMessageBody: React.FC<Omit<MessageBodyProps, 'isUser'>> = ({
|
||||
const openMultiRunLauncherWithPrompt = useUIStore((state) => state.openMultiRunLauncherWithPrompt);
|
||||
const isLastAssistantInTurn = turnGroupingContext?.isLastAssistantInTurn ?? false;
|
||||
const hasStopFinish = messageFinish === 'stop';
|
||||
|
||||
// TTS for message playback
|
||||
const { isPlaying: isTTSPlaying, play: playTTS, stop: stopTTS } = useMessageTTS();
|
||||
const showMessageTTSButtons = useConfigStore((state) => state.showMessageTTSButtons);
|
||||
const voiceProvider = useConfigStore((state) => state.voiceProvider);
|
||||
|
||||
const readAloudTooltip = React.useMemo(() => {
|
||||
if (isTTSPlaying) {
|
||||
return 'Stop speaking';
|
||||
}
|
||||
const providerLabel = voiceProvider === 'browser' ? 'Browser' : voiceProvider === 'openai' ? 'OpenAI' : 'Say';
|
||||
return `Read aloud (${providerLabel} voice)`;
|
||||
}, [isTTSPlaying, voiceProvider]);
|
||||
|
||||
|
||||
const hasTools = toolParts.length > 0;
|
||||
@@ -503,6 +518,24 @@ const AssistantMessageBody: React.FC<Omit<MessageBodyProps, 'isUser'>> = ({
|
||||
[assistantTextParts, openMultiRunLauncherWithPrompt]
|
||||
);
|
||||
|
||||
const handleTTSClick = React.useCallback(
|
||||
(event: React.MouseEvent<HTMLButtonElement>) => {
|
||||
event.stopPropagation();
|
||||
event.preventDefault();
|
||||
|
||||
if (isTTSPlaying) {
|
||||
stopTTS();
|
||||
return;
|
||||
}
|
||||
|
||||
const messageText = flattenAssistantTextParts(assistantTextParts);
|
||||
if (messageText.trim()) {
|
||||
void playTTS(messageText);
|
||||
}
|
||||
},
|
||||
[assistantTextParts, isTTSPlaying, playTTS, stopTTS]
|
||||
);
|
||||
|
||||
React.useEffect(() => {
|
||||
return () => {
|
||||
clearCopyHintTimeout();
|
||||
@@ -882,6 +915,31 @@ const AssistantMessageBody: React.FC<Omit<MessageBodyProps, 'isUser'>> = ({
|
||||
<TooltipContent sideOffset={6}>Start new multi-run from this answer</TooltipContent>
|
||||
</Tooltip>
|
||||
|
||||
{showMessageTTSButtons && hasCopyableText && (
|
||||
<Tooltip delayDuration={1000}>
|
||||
<TooltipTrigger asChild>
|
||||
<Button
|
||||
type="button"
|
||||
variant="ghost"
|
||||
size="icon"
|
||||
className={cn(
|
||||
'h-8 w-8 bg-transparent hover:!bg-transparent active:!bg-transparent focus-visible:!bg-transparent focus-visible:ring-2 focus-visible:ring-primary/50',
|
||||
isTTSPlaying ? 'text-green-500' : 'text-muted-foreground hover:text-foreground'
|
||||
)}
|
||||
aria-label={isTTSPlaying ? 'Stop speaking' : 'Read aloud'}
|
||||
onPointerDown={(event) => event.stopPropagation()}
|
||||
onClick={handleTTSClick}
|
||||
>
|
||||
{isTTSPlaying ? (
|
||||
<RiStopLine className="h-3.5 w-3.5" />
|
||||
) : (
|
||||
<RiVolumeUpLine className="h-3.5 w-3.5" />
|
||||
)}
|
||||
</Button>
|
||||
</TooltipTrigger>
|
||||
<TooltipContent sideOffset={6}>{readAloudTooltip}</TooltipContent>
|
||||
</Tooltip>
|
||||
)}
|
||||
{onCopyMessage && (
|
||||
<Tooltip delayDuration={1000}>
|
||||
<TooltipTrigger asChild>
|
||||
|
||||
Reference in New Issue
Block a user