chore: import upstream snapshot with attribution

apps/sim/lib/api/contracts/media/index.ts

@@ -0,0 +1,2 @@
+export * from '@/lib/api/contracts/media/speech'
+export * from '@/lib/api/contracts/media/tts-stream'

apps/sim/lib/api/contracts/media/speech.ts

@@ -0,0 +1,21 @@
+import { z } from 'zod'
+import { defineRouteContract } from '@/lib/api/contracts/types'
+
+export const speechTokenBodySchema = z
+  .object({
+    chatId: z.string().optional(),
+    /** Editor/workspace voice: the workspace the session user is recording in. */
+    workspaceId: z.string().optional(),
+  })
+  .passthrough()
+
+export const speechTokenResponseSchema = z.object({
+  token: z.string(),
+})
+
+export const speechTokenContract = defineRouteContract({
+  method: 'POST',
+  path: '/api/speech/token',
+  body: speechTokenBodySchema,
+  response: { mode: 'json', schema: speechTokenResponseSchema },
+})

apps/sim/lib/api/contracts/media/tts-stream.ts

@@ -0,0 +1,18 @@
+import { z } from 'zod'
+import { defineRouteContract } from '@/lib/api/contracts/types'
+
+export const ttsStreamBodySchema = z
+  .object({
+    text: z.string().min(1),
+    voiceId: z.string().min(1),
+    modelId: z.string().optional().default('eleven_flash_v2_5'),
+    chatId: z.string().min(1),
+  })
+  .passthrough()
+
+export const ttsStreamContract = defineRouteContract({
+  method: 'POST',
+  path: '/api/proxy/tts/stream',
+  body: ttsStreamBodySchema,
+  response: { mode: 'stream' },
+})