chore(chat): remove deployed-chat voice mode (#6215)

Removes the voice-first interface and TTS playback from the deployed
chat, keeping workspace dictation, which is a separate feature.

- Deletes the VoiceInterface UI and its particles canvas, the chat mic
  input, the TTS audio-streaming hook, the /api/proxy/tts/stream relay
  and its contract, and the voice-settings query hook.
- Unpicks the voice wiring in chat.tsx and use-chat-streaming: the
  audio stream handler, sentence-splitting for speech, voice-first mode
  state, and the isVoiceInput plumbing through ChatInput.
- Drops the now-dead chatId branch from /api/speech/token. It was the
  anonymous public-chat path; with no caller left it would have stayed
  an unauthenticated relay spending the platform key. That leaves
  resolveDeployedChatCaller unused, so it goes too.
- Removes code the above orphaned: MAX_CHAT_SESSION_MS, the noop util,
  the audio/position refs in use-chat-streaming that were only ever
  written, and the chatId field on the speech contract.

Keeps /api/settings/voice, lib/speech and use-speech-to-text: the
workspace home input still uses them. Keeps the voice-output usage
source, enum and label — Postgres cannot drop an enum value, and
historical usage_log rows still need a label to render.

Author: waleedlatif1

apps/sim/app/(interfaces)/chat/[identifier]/chat.tsx

@@ -3,8 +3,6 @@
 import { type RefObject, useCallback, useEffect, useMemo, useRef, useState } from 'react'
 import { createLogger } from '@sim/logger'
 import { generateId } from '@sim/utils/id'
-import { DEFAULT_TTS_VOICE_ID } from '@/lib/api/contracts/media/tts-stream'
-import { noop } from '@/lib/core/utils/request'
 import {
   AGENT_STREAM_PROTOCOL_HEADER,
   AGENT_STREAM_PROTOCOL_V1,
@@ -19,23 +17,15 @@ import {
   ChatMessageContainer,
   EmailAuth,
   PasswordAuth,
-  VoiceInterface,
 } from '@/app/(interfaces)/chat/components'
 import { CHAT_ERROR_MESSAGES, CHAT_REQUEST_TIMEOUT_MS } from '@/app/(interfaces)/chat/constants'
-import { useAudioStreaming, useChatStreaming } from '@/app/(interfaces)/chat/hooks'
+import { useChatStreaming } from '@/app/(interfaces)/chat/hooks'
 import SSOAuth from '@/ee/sso/components/sso-auth'
 import { useDeployedChatConfig } from '@/hooks/queries/chats'
 import { useGitHubStars } from '@/hooks/queries/github-stars'
-import { useVoiceSettings } from '@/hooks/queries/voice-settings'
 
 const logger = createLogger('ChatClient')
 
-interface AudioStreamingOptions {
-  voiceId: string
-  chatId: string
-  onError: (error: Error) => void
-}
-
 interface ChatRequestFile {
   name: string
   size: number
@@ -49,10 +39,6 @@ interface ChatRequestPayload {
   files?: ChatRequestFile[]
 }
 
-const DEFAULT_VOICE_SETTINGS = {
-  voiceId: DEFAULT_TTS_VOICE_ID,
-}
-
 /**
  * Converts a File object to a base64 data URL
  */
@@ -65,33 +51,6 @@ function fileToBase64(file: File): Promise<string> {
   })
 }
 
-/**
- * Creates an audio stream handler for text-to-speech conversion
- * @param streamTextToAudio - Function to stream text to audio
- * @param voiceId - The voice ID to use for TTS
- * @param chatId - Optional chat ID for deployed chat authentication
- * @returns Audio stream handler function or undefined
- */
-function createAudioStreamHandler(
-  streamTextToAudio: (text: string, options: AudioStreamingOptions) => Promise<void>,
-  voiceId: string,
-  chatId: string
-) {
-  return async (text: string) => {
-    try {
-      await streamTextToAudio(text, {
-        voiceId,
-        chatId,
-        onError: (error: Error) => {
-          logger.error('Audio streaming error:', error)
-        },
-      })
-    } catch (error) {
-      logger.error('TTS error:', error)
-    }
-  }
-}
-
 export default function ChatClient({ identifier }: { identifier: string }) {
   const [messages, setMessages] = useState<ChatMessage[]>([])
   const [inputValue, setInputValue] = useState('')
@@ -105,13 +64,9 @@ export default function ChatClient({ identifier }: { identifier: string }) {
   const stickToBottomRef = useRef(true)
   const ignoreScrollRef = useRef(false)
 
-  const [isVoiceFirstMode, setIsVoiceFirstMode] = useState(false)
-
   const { data: chatConfigResult, error: chatConfigError } = useDeployedChatConfig(identifier)
-  const { data: voiceSettings } = useVoiceSettings()
   const { data: starCount } = useGitHubStars()
 
-  const sttAvailable = voiceSettings?.sttAvailable === true
   const authRequired = chatConfigResult?.kind === 'auth' ? chatConfigResult.authType : null
   const chatConfig = chatConfigResult?.kind === 'config' ? chatConfigResult.config : null
 
@@ -135,8 +90,6 @@ export default function ChatClient({ identifier }: { identifier: string }) {
 
   const { isStreamingResponse, abortControllerRef, stopStreaming, handleStreamedResponse } =
     useChatStreaming()
-  const audioContextRef = useRef<AudioContext | null>(null)
-  const { isPlayingAudio, streamTextToAudio, stopAudio } = useAudioStreaming(audioContextRef)
 
   const NEAR_BOTTOM_THRESHOLD_PX = 100
 
@@ -208,11 +161,10 @@ export default function ChatClient({ identifier }: { identifier: string }) {
 
     container.addEventListener('scroll', handleScroll, { passive: true })
     return () => container.removeEventListener('scroll', handleScroll)
-  }, [chatConfig, isVoiceFirstMode, authRequired])
+  }, [chatConfig, authRequired])
 
   const handleSendMessage = async (
     messageParam?: string,
-    isVoiceInput = false,
     files?: Array<{
       id: string
       name: string
@@ -227,7 +179,6 @@ export default function ChatClient({ identifier }: { identifier: string }) {
 
     logger.info('Sending message:', {
       messageToSend,
-      isVoiceInput,
       conversationId,
       filesCount: files?.length,
     })
@@ -316,30 +267,12 @@ export default function ChatClient({ identifier }: { identifier: string }) {
         throw new Error('Response body is missing')
       }
 
-      const shouldPlayAudio = isVoiceInput || isVoiceFirstMode
-      const audioHandler =
-        shouldPlayAudio && chatConfig?.id
-          ? createAudioStreamHandler(
-              streamTextToAudio,
-              DEFAULT_VOICE_SETTINGS.voiceId,
-              chatConfig.id
-            )
-          : undefined
-
-      logger.info('Starting to handle streamed response:', { shouldPlayAudio })
-
       await handleStreamedResponse(
         response,
         setMessages,
         setIsLoading,
         () => scrollToBottom({ behavior: 'auto' }),
         {
-          voiceSettings: {
-            isVoiceEnabled: shouldPlayAudio,
-            voiceId: DEFAULT_VOICE_SETTINGS.voiceId,
-            autoPlayResponses: shouldPlayAudio,
-          },
-          audioStreamHandler: audioHandler,
           outputConfigs: chatConfig?.outputConfigs,
           abortController,
         }
@@ -365,41 +298,6 @@ export default function ChatClient({ identifier }: { identifier: string }) {
     }
   }
 
-  useEffect(() => {
-    return () => {
-      stopAudio()
-      if (audioContextRef.current && audioContextRef.current.state !== 'closed') {
-        audioContextRef.current.close()
-      }
-    }
-  }, [stopAudio])
-
-  const handleVoiceInterruption = useCallback(() => {
-    stopAudio()
-
-    if (isStreamingResponse) {
-      stopStreaming(setMessages)
-    }
-  }, [isStreamingResponse, stopStreaming, setMessages, stopAudio])
-
-  const handleVoiceStart = useCallback(() => {
-    if (!sttAvailable) return
-    setIsVoiceFirstMode(true)
-  }, [sttAvailable])
-
-  const handleExitVoiceMode = useCallback(() => {
-    setIsVoiceFirstMode(false)
-    stopAudio()
-  }, [stopAudio])
-
-  const handleVoiceTranscript = useCallback(
-    (transcript: string) => {
-      logger.info('Received voice transcript:', transcript)
-      handleSendMessage(transcript, true)
-    },
-    [handleSendMessage]
-  )
-
   if (chatConfigError) {
     logger.error('Error fetching chat config:', chatConfigError)
     return <ChatErrorState error={CHAT_ERROR_MESSAGES.CHAT_UNAVAILABLE} />
@@ -421,26 +319,6 @@ export default function ChatClient({ identifier }: { identifier: string }) {
     return <ChatLoadingState />
   }
 
-  if (isVoiceFirstMode) {
-    return (
-      <VoiceInterface
-        onCallEnd={handleExitVoiceMode}
-        onVoiceTranscript={handleVoiceTranscript}
-        onVoiceStart={noop}
-        onVoiceEnd={noop}
-        onInterrupt={handleVoiceInterruption}
-        isStreaming={isStreamingResponse}
-        isPlayingAudio={isPlayingAudio}
-        audioContextRef={audioContextRef}
-        chatId={chatConfig?.id}
-        messages={displayMessages.map((msg) => ({
-          content: typeof msg.content === 'string' ? msg.content : JSON.stringify(msg.content),
-          type: msg.type,
-        }))}
-      />
-    )
-  }
-
   return (
     <div className='light desktop-title-bar-page fixed inset-0 z-[100] flex flex-col bg-[var(--bg)] text-[var(--text-primary)]'>
       <DesktopTitleBarLane />
@@ -463,13 +341,11 @@ export default function ChatClient({ identifier }: { identifier: string }) {
       <div className='relative p-3 pb-4 md:p-4 md:pb-6'>
         <div className='relative mx-auto max-w-3xl md:max-w-[748px]'>
           <ChatInput
-            onSubmit={(value, isVoiceInput, files) => {
-              void handleSendMessage(value, isVoiceInput, files)
+            onSubmit={(value, files) => {
+              void handleSendMessage(value, files)
             }}
             isStreaming={isStreamingResponse}
             onStopStreaming={() => stopStreaming(setMessages)}
-            onVoiceStart={handleVoiceStart}
-            sttAvailable={sttAvailable}
           />
         </div>
       </div>

apps/sim/app/(interfaces)/chat/components/index.ts

@@ -6,4 +6,3 @@ export { ChatInput } from './input/input'
 export { ChatLoadingState } from './loading-state/loading-state'
 export type { ChatMessage } from './message/message'
 export { ChatMessageContainer } from './message-container/message-container'
-export { VoiceInterface } from './voice-interface/voice-interface'

apps/sim/app/(interfaces)/chat/components/input/input.tsx

@@ -5,9 +5,8 @@ import { useCallback, useLayoutEffect, useRef, useState } from 'react'
 import { Badge, Button, cn, handleKeyboardActivation, Tooltip } from '@sim/emcn'
 import { createLogger } from '@sim/logger'
 import { generateId } from '@sim/utils/id'
-import { ArrowUp, Mic, Paperclip, X } from 'lucide-react'
+import { ArrowUp, Paperclip, X } from 'lucide-react'
 import { CHAT_ACCEPT_ATTRIBUTE } from '@/lib/uploads/utils/validation'
-import { VoiceInput } from '@/app/(interfaces)/chat/components/input/voice-input'
 
 const logger = createLogger('ChatInput')
 
@@ -23,20 +22,10 @@ interface AttachedFile {
 }
 
 export const ChatInput: React.FC<{
-  onSubmit?: (value: string, isVoiceInput?: boolean, files?: AttachedFile[]) => void
+  onSubmit?: (value: string, files?: AttachedFile[]) => void
   isStreaming?: boolean
   onStopStreaming?: () => void
-  onVoiceStart?: () => void
-  voiceOnly?: boolean
-  sttAvailable?: boolean
-}> = ({
-  onSubmit,
-  isStreaming = false,
-  onStopStreaming,
-  onVoiceStart,
-  voiceOnly = false,
-  sttAvailable = false,
-}) => {
+}> = ({ onSubmit, isStreaming = false, onStopStreaming }) => {
   const fileInputRef = useRef<HTMLInputElement>(null)
   const textareaRef = useRef<HTMLTextAreaElement>(null)
   const [inputValue, setInputValue] = useState('')
@@ -114,7 +103,7 @@ export const ChatInput: React.FC<{
   const handleSubmit = useCallback(() => {
     if (isStreaming) return
     if (!inputValue.trim() && attachedFiles.length === 0) return
-    onSubmit?.(inputValue.trim(), false, attachedFiles)
+    onSubmit?.(inputValue.trim(), attachedFiles)
     setInputValue('')
     setAttachedFiles([])
     setUploadErrors([])
@@ -141,31 +130,6 @@ export const ChatInput: React.FC<{
 
   const canSubmit = (inputValue.trim().length > 0 || attachedFiles.length > 0) && !isStreaming
 
-  if (voiceOnly) {
-    return (
-      <Tooltip.Provider>
-        <div className='flex items-center justify-center'>
-          {sttAvailable && (
-            <Tooltip.Root>
-              <Tooltip.Trigger asChild>
-                <div>
-                  <VoiceInput
-                    onVoiceStart={onVoiceStart ?? (() => {})}
-                    disabled={isStreaming}
-                    large={true}
-                  />
-                </div>
-              </Tooltip.Trigger>
-              <Tooltip.Content side='top'>
-                <p>Start voice conversation</p>
-              </Tooltip.Content>
-            </Tooltip.Root>
-          )}
-        </div>
-      </Tooltip.Provider>
-    )
-  }
-
   return (
     <Tooltip.Provider>
       <div className='fixed right-0 bottom-0 left-0 flex w-full items-center justify-center bg-gradient-to-t from-[var(--bg)] to-transparent px-4 pb-4 md:px-0 md:pb-4'>
@@ -302,26 +266,8 @@ export const ChatInput: React.FC<{
                 />
               </div>
 
-              {/* Right: mic + send */}
+              {/* Right: send */}
               <div className='flex items-center gap-1.5'>
-                {sttAvailable && (
-                  <Tooltip.Root>
-                    <Tooltip.Trigger asChild>
-                      <Button
-                        variant='quiet'
-                        onClick={onVoiceStart}
-                        disabled={isStreaming}
-                        className='size-[28px] rounded-full p-0'
-                      >
-                        <Mic className='size-[16px]' strokeWidth={2} />
-                      </Button>
-                    </Tooltip.Trigger>
-                    <Tooltip.Content side='top'>
-                      <p>Start voice conversation</p>
-                    </Tooltip.Content>
-                  </Tooltip.Root>
-                )}
-
                 {isStreaming ? (
                   <Button
                     variant='primary'