fix(security): meter and throttle the deployed-chat TTS relay

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

@@ -3,6 +3,7 @@
 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,
@@ -49,7 +50,7 @@ interface ChatRequestPayload {
 }
 
 const DEFAULT_VOICE_SETTINGS = {
-  voiceId: 'cgSgspJ2msm6clMCkdW9', // Default ElevenLabs voice (Jessica) — Flash v2.5-optimized
+  voiceId: DEFAULT_TTS_VOICE_ID,
 }
 
 /**

apps/sim/app/(interfaces)/chat/hooks/use-audio-streaming.test.ts

@@ -0,0 +1,57 @@
+/**
+ * @vitest-environment node
+ */
+import { describe, expect, it } from 'vitest'
+import { MAX_TTS_TEXT_LENGTH } from '@/lib/api/contracts/media/tts-stream'
+import { splitForSynthesis } from '@/app/(interfaces)/chat/hooks/use-audio-streaming'
+
+describe('splitForSynthesis', () => {
+  it('leaves text within the relay cap untouched', () => {
+    expect(splitForSynthesis('Short answer.')).toEqual(['Short answer.'])
+  })
+
+  /**
+   * The caller only sentence-splits on Western `.!?`, so CJK punctuation never
+   * matches and the whole answer arrives as one block. Before splitting, the
+   * relay rejected it and the message played no audio at all.
+   */
+  it('splits CJK text that never matches the Western sentence split', () => {
+    const text = '这是一个很长的回答。'.repeat(400)
+    expect(text.length).toBeGreaterThan(MAX_TTS_TEXT_LENGTH)
+
+    const chunks = splitForSynthesis(text)
+
+    expect(chunks.length).toBeGreaterThan(1)
+    for (const chunk of chunks) {
+      expect(chunk.length).toBeLessThanOrEqual(MAX_TTS_TEXT_LENGTH)
+    }
+  })
+
+  it('splits a long list that has no terminal punctuation', () => {
+    const text = Array.from({ length: 300 }, (_, i) => `- item number ${i}`).join('\n')
+    expect(text.length).toBeGreaterThan(MAX_TTS_TEXT_LENGTH)
+
+    const chunks = splitForSynthesis(text)
+
+    for (const chunk of chunks) {
+      expect(chunk.length).toBeLessThanOrEqual(MAX_TTS_TEXT_LENGTH)
+    }
+  })
+
+  it('preserves the spoken content across chunks', () => {
+    const text = Array.from({ length: 500 }, (_, i) => `word${i}`).join(' ')
+
+    const chunks = splitForSynthesis(text)
+
+    expect(chunks.join(' ').replace(/\s+/g, ' ')).toBe(text)
+  })
+
+  it('still caps text with no break opportunity at all', () => {
+    const chunks = splitForSynthesis('a'.repeat(MAX_TTS_TEXT_LENGTH * 2 + 5))
+
+    expect(chunks.length).toBe(3)
+    for (const chunk of chunks) {
+      expect(chunk.length).toBeLessThanOrEqual(MAX_TTS_TEXT_LENGTH)
+    }
+  })
+})

apps/sim/app/(interfaces)/chat/hooks/use-audio-streaming.ts

@@ -2,9 +2,47 @@
 
 import { type RefObject, useCallback, useRef, useState } from 'react'
 import { createLogger } from '@sim/logger'
+import { DEFAULT_TTS_MODEL_ID, MAX_TTS_TEXT_LENGTH } from '@/lib/api/contracts/media/tts-stream'
 
 const logger = createLogger('UseAudioStreaming')
 
+/** Prefer breaking on a boundary this far into the chunk before splitting mid-word. */
+const MIN_SPLIT_RATIO = 0.6
+
+/**
+ * Splits text into pieces the TTS relay will accept.
+ *
+ * The caller sentence-splits on Western `.!?` only, so text that never matches
+ * — CJK punctuation, or a list with no terminal punctuation — reaches this hook
+ * as one accumulated block that can exceed the relay's per-request cap. Without
+ * splitting, the relay rejects it and the whole message plays no audio.
+ */
+export function splitForSynthesis(text: string, max: number = MAX_TTS_TEXT_LENGTH): string[] {
+  if (text.length <= max) return [text]
+
+  const chunks: string[] = []
+  let rest = text
+
+  while (rest.length > max) {
+    const window = rest.slice(0, max)
+    const boundary = Math.max(
+      window.lastIndexOf(' '),
+      window.lastIndexOf('\n'),
+      window.lastIndexOf('。'),
+      window.lastIndexOf('，'),
+      window.lastIndexOf('、')
+    )
+    const cut = boundary >= max * MIN_SPLIT_RATIO ? boundary + 1 : max
+    const piece = rest.slice(0, cut).trim()
+    if (piece) chunks.push(piece)
+    rest = rest.slice(cut)
+  }
+
+  const tail = rest.trim()
+  if (tail) chunks.push(tail)
+  return chunks
+}
+
 declare global {
   interface Window {
     webkitAudioContext?: typeof AudioContext
@@ -79,7 +117,7 @@ export function useAudioStreaming(sharedAudioContextRef?: RefObject<AudioContext
     const { text, options } = item
     const {
       voiceId,
-      modelId = 'eleven_flash_v2_5',
+      modelId = DEFAULT_TTS_MODEL_ID,
       chatId,
       onAudioStart,
       onAudioEnd,
@@ -156,7 +194,9 @@ export function useAudioStreaming(sharedAudioContextRef?: RefObject<AudioContext
         abortControllerRef.current = new AbortController()
       }
 
-      audioQueueRef.current.push({ text, options })
+      for (const piece of splitForSynthesis(text)) {
+        audioQueueRef.current.push({ text: piece, options })
+      }
       processAudioQueue()
     },
     [processAudioQueue]