@clawdbot/voice-call 2026.1.21 → 2026.1.24

package/CHANGELOG.md

@@ -1,5 +1,22 @@
 # Changelog
 
+## 2026.1.24
+
+### Changes
+- Breaking: voice-call TTS now uses core `messages.tts` (plugin TTS config deep‑merges with core).
+- Telephony TTS supports OpenAI + ElevenLabs; Edge TTS is ignored for calls.
+- Removed legacy `tts.model`/`tts.voice`/`tts.instructions` plugin fields.
+
+## 2026.1.23
+
+### Changes
+- Version alignment with core Clawdbot release numbers.
+
+## 2026.1.22
+
+### Changes
+- Version alignment with core Clawdbot release numbers.
+
 ## 2026.1.21
 
 ### Changes

package/README.md

@@ -75,6 +75,27 @@ Notes:
 - Twilio/Telnyx/Plivo require a **publicly reachable** webhook URL.
 - `mock` is a local dev provider (no network calls).
 
+## TTS for calls
+
+Voice Call uses the core `messages.tts` configuration (OpenAI or ElevenLabs) for
+streaming speech on calls. You can override it under the plugin config with the
+same shape — overrides deep-merge with `messages.tts`.
+
+```json5
+{
+  tts: {
+    provider: "openai",
+    openai: {
+      voice: "alloy"
+    }
+  }
+}
+```
+
+Notes:
+- Edge TTS is ignored for voice calls (telephony audio needs PCM; Edge output is unreliable).
+- Core TTS is used when Twilio media streaming is enabled; otherwise calls fall back to provider native voices.
+
 ## CLI
 
 ```bash

package/clawdbot.plugin.json

@@ -99,16 +99,39 @@
       "label": "Media Stream Path",
       "advanced": true
     },
-    "tts.model": {
-      "label": "TTS Model",
+    "tts.provider": {
+      "label": "TTS Provider Override",
+      "help": "Deep-merges with messages.tts (Edge is ignored for calls).",
       "advanced": true
     },
-    "tts.voice": {
-      "label": "TTS Voice",
+    "tts.openai.model": {
+      "label": "OpenAI TTS Model",
       "advanced": true
     },
-    "tts.instructions": {
-      "label": "TTS Instructions",
+    "tts.openai.voice": {
+      "label": "OpenAI TTS Voice",
+      "advanced": true
+    },
+    "tts.openai.apiKey": {
+      "label": "OpenAI API Key",
+      "sensitive": true,
+      "advanced": true
+    },
+    "tts.elevenlabs.modelId": {
+      "label": "ElevenLabs Model ID",
+      "advanced": true
+    },
+    "tts.elevenlabs.voiceId": {
+      "label": "ElevenLabs Voice ID",
+      "advanced": true
+    },
+    "tts.elevenlabs.apiKey": {
+      "label": "ElevenLabs API Key",
+      "sensitive": true,
+      "advanced": true
+    },
+    "tts.elevenlabs.baseUrl": {
+      "label": "ElevenLabs Base URL",
       "advanced": true
     },
     "publicUrl": {
@@ -370,20 +393,193 @@
         "type": "object",
         "additionalProperties": false,
         "properties": {
+          "auto": {
+            "type": "string",
+            "enum": [
+              "off",
+              "always",
+              "inbound",
+              "tagged"
+            ]
+          },
+          "enabled": {
+            "type": "boolean"
+          },
+          "mode": {
+            "type": "string",
+            "enum": [
+              "final",
+              "all"
+            ]
+          },
           "provider": {
             "type": "string",
             "enum": [
-              "openai"
+              "openai",
+              "elevenlabs",
+              "edge"
             ]
           },
-          "model": {
+          "summaryModel": {
             "type": "string"
           },
-          "voice": {
-            "type": "string"
+          "modelOverrides": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+              "enabled": {
+                "type": "boolean"
+              },
+              "allowText": {
+                "type": "boolean"
+              },
+              "allowProvider": {
+                "type": "boolean"
+              },
+              "allowVoice": {
+                "type": "boolean"
+              },
+              "allowModelId": {
+                "type": "boolean"
+              },
+              "allowVoiceSettings": {
+                "type": "boolean"
+              },
+              "allowNormalization": {
+                "type": "boolean"
+              },
+              "allowSeed": {
+                "type": "boolean"
+              }
+            }
+          },
+          "elevenlabs": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+              "apiKey": {
+                "type": "string"
+              },
+              "baseUrl": {
+                "type": "string"
+              },
+              "voiceId": {
+                "type": "string"
+              },
+              "modelId": {
+                "type": "string"
+              },
+              "seed": {
+                "type": "integer",
+                "minimum": 0,
+                "maximum": 4294967295
+              },
+              "applyTextNormalization": {
+                "type": "string",
+                "enum": [
+                  "auto",
+                  "on",
+                  "off"
+                ]
+              },
+              "languageCode": {
+                "type": "string"
+              },
+              "voiceSettings": {
+                "type": "object",
+                "additionalProperties": false,
+                "properties": {
+                  "stability": {
+                    "type": "number",
+                    "minimum": 0,
+                    "maximum": 1
+                  },
+                  "similarityBoost": {
+                    "type": "number",
+                    "minimum": 0,
+                    "maximum": 1
+                  },
+                  "style": {
+                    "type": "number",
+                    "minimum": 0,
+                    "maximum": 1
+                  },
+                  "useSpeakerBoost": {
+                    "type": "boolean"
+                  },
+                  "speed": {
+                    "type": "number",
+                    "minimum": 0.5,
+                    "maximum": 2
+                  }
+                }
+              }
+            }
+          },
+          "openai": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+              "apiKey": {
+                "type": "string"
+              },
+              "model": {
+                "type": "string"
+              },
+              "voice": {
+                "type": "string"
+              }
+            }
           },
-          "instructions": {
+          "edge": {
+            "type": "object",
+            "additionalProperties": false,
+            "properties": {
+              "enabled": {
+                "type": "boolean"
+              },
+              "voice": {
+                "type": "string"
+              },
+              "lang": {
+                "type": "string"
+              },
+              "outputFormat": {
+                "type": "string"
+              },
+              "pitch": {
+                "type": "string"
+              },
+              "rate": {
+                "type": "string"
+              },
+              "volume": {
+                "type": "string"
+              },
+              "saveSubtitles": {
+                "type": "boolean"
+              },
+              "proxy": {
+                "type": "string"
+              },
+              "timeoutMs": {
+                "type": "integer",
+                "minimum": 1000,
+                "maximum": 120000
+              }
+            }
+          },
+          "prefsPath": {
             "type": "string"
+          },
+          "maxTextLength": {
+            "type": "integer",
+            "minimum": 1
+          },
+          "timeoutMs": {
+            "type": "integer",
+            "minimum": 1000,
+            "maximum": 120000
           }
         }
       },

package/index.ts

@@ -74,9 +74,26 @@ const voiceCallConfigSchema = {
     },
     "streaming.sttModel": { label: "Realtime STT Model", advanced: true },
     "streaming.streamPath": { label: "Media Stream Path", advanced: true },
-    "tts.model": { label: "TTS Model", advanced: true },
-    "tts.voice": { label: "TTS Voice", advanced: true },
-    "tts.instructions": { label: "TTS Instructions", advanced: true },
+    "tts.provider": {
+      label: "TTS Provider Override",
+      help: "Deep-merges with messages.tts (Edge is ignored for calls).",
+      advanced: true,
+    },
+    "tts.openai.model": { label: "OpenAI TTS Model", advanced: true },
+    "tts.openai.voice": { label: "OpenAI TTS Voice", advanced: true },
+    "tts.openai.apiKey": {
+      label: "OpenAI API Key",
+      sensitive: true,
+      advanced: true,
+    },
+    "tts.elevenlabs.modelId": { label: "ElevenLabs Model ID", advanced: true },
+    "tts.elevenlabs.voiceId": { label: "ElevenLabs Voice ID", advanced: true },
+    "tts.elevenlabs.apiKey": {
+      label: "ElevenLabs API Key",
+      sensitive: true,
+      advanced: true,
+    },
+    "tts.elevenlabs.baseUrl": { label: "ElevenLabs Base URL", advanced: true },
     publicUrl: { label: "Public Webhook URL", advanced: true },
     skipSignatureVerification: {
       label: "Skip Signature Verification",
@@ -161,6 +178,7 @@ const voiceCallPlugin = {
         runtimePromise = createVoiceCallRuntime({
           config: cfg,
           coreConfig: api.config as CoreConfig,
+          ttsRuntime: api.runtime.tts,
           logger: api.logger,
         });
       }

package/package.json

@@ -1,12 +1,12 @@
 {
   "name": "@clawdbot/voice-call",
-  "version": "2026.1.21",
+  "version": "2026.1.24",
   "type": "module",
   "description": "Clawdbot voice-call plugin",
   "dependencies": {
     "@sinclair/typebox": "0.34.47",
     "ws": "^8.19.0",
-    "zod": "^4.3.5"
+    "zod": "^4.3.6"
   },
   "clawdbot": {
     "extensions": [

package/src/config.ts

@@ -82,31 +82,82 @@ export const SttConfigSchema = z
   .default({ provider: "openai", model: "whisper-1" });
 export type SttConfig = z.infer<typeof SttConfigSchema>;
 
+export const TtsProviderSchema = z.enum(["openai", "elevenlabs", "edge"]);
+export const TtsModeSchema = z.enum(["final", "all"]);
+export const TtsAutoSchema = z.enum(["off", "always", "inbound", "tagged"]);
+
 export const TtsConfigSchema = z
   .object({
-    /** TTS provider (currently only OpenAI supported) */
-    provider: z.literal("openai").default("openai"),
-    /**
-     * TTS model to use:
-     * - gpt-4o-mini-tts: newest, supports instructions for tone/style control (recommended)
-     * - tts-1: lower latency
-     * - tts-1-hd: higher quality
-     */
-    model: z.string().min(1).default("gpt-4o-mini-tts"),
-    /**
-     * Voice ID. For best quality, use marin or cedar.
-     * All voices: alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, shimmer, verse, marin, cedar
-     */
-    voice: z.string().min(1).default("coral"),
-    /**
-     * Instructions for speech style (only works with gpt-4o-mini-tts).
-     * Examples: "Speak in a cheerful tone", "Talk like a sympathetic customer service agent"
-     */
-    instructions: z.string().optional(),
+    auto: TtsAutoSchema.optional(),
+    enabled: z.boolean().optional(),
+    mode: TtsModeSchema.optional(),
+    provider: TtsProviderSchema.optional(),
+    summaryModel: z.string().optional(),
+    modelOverrides: z
+      .object({
+        enabled: z.boolean().optional(),
+        allowText: z.boolean().optional(),
+        allowProvider: z.boolean().optional(),
+        allowVoice: z.boolean().optional(),
+        allowModelId: z.boolean().optional(),
+        allowVoiceSettings: z.boolean().optional(),
+        allowNormalization: z.boolean().optional(),
+        allowSeed: z.boolean().optional(),
+      })
+      .strict()
+      .optional(),
+    elevenlabs: z
+      .object({
+        apiKey: z.string().optional(),
+        baseUrl: z.string().optional(),
+        voiceId: z.string().optional(),
+        modelId: z.string().optional(),
+        seed: z.number().int().min(0).max(4294967295).optional(),
+        applyTextNormalization: z.enum(["auto", "on", "off"]).optional(),
+        languageCode: z.string().optional(),
+        voiceSettings: z
+          .object({
+            stability: z.number().min(0).max(1).optional(),
+            similarityBoost: z.number().min(0).max(1).optional(),
+            style: z.number().min(0).max(1).optional(),
+            useSpeakerBoost: z.boolean().optional(),
+            speed: z.number().min(0.5).max(2).optional(),
+          })
+          .strict()
+          .optional(),
+      })
+      .strict()
+      .optional(),
+    openai: z
+      .object({
+        apiKey: z.string().optional(),
+        model: z.string().optional(),
+        voice: z.string().optional(),
+      })
+      .strict()
+      .optional(),
+    edge: z
+      .object({
+        enabled: z.boolean().optional(),
+        voice: z.string().optional(),
+        lang: z.string().optional(),
+        outputFormat: z.string().optional(),
+        pitch: z.string().optional(),
+        rate: z.string().optional(),
+        volume: z.string().optional(),
+        saveSubtitles: z.boolean().optional(),
+        proxy: z.string().optional(),
+        timeoutMs: z.number().int().min(1000).max(120000).optional(),
+      })
+      .strict()
+      .optional(),
+    prefsPath: z.string().optional(),
+    maxTextLength: z.number().int().min(1).optional(),
+    timeoutMs: z.number().int().min(1000).max(120000).optional(),
   })
   .strict()
-  .default({ provider: "openai", model: "gpt-4o-mini-tts", voice: "coral" });
-export type TtsConfig = z.infer<typeof TtsConfigSchema>;
+  .optional();
+export type VoiceCallTtsConfig = z.infer<typeof TtsConfigSchema>;
 
 // -----------------------------------------------------------------------------
 // Webhook Server Configuration
@@ -307,7 +358,7 @@ export const VoiceCallConfigSchema = z
   /** STT configuration */
   stt: SttConfigSchema,
 
-  /** TTS configuration */
+  /** TTS override (deep-merges with core messages.tts) */
   tts: TtsConfigSchema,
 
   /** Store path for call logs */

package/src/core-bridge.ts

@@ -2,10 +2,16 @@ import fs from "node:fs";
 import path from "node:path";
 import { fileURLToPath, pathToFileURL } from "node:url";
 
+import type { VoiceCallTtsConfig } from "./config.js";
+
 export type CoreConfig = {
   session?: {
     store?: string;
   };
+  messages?: {
+    tts?: VoiceCallTtsConfig;
+  };
+  [key: string]: unknown;
 };
 
 type CoreAgentDeps = {

package/src/manager/context.ts

@@ -19,4 +19,3 @@ export type CallManagerContext = {
   transcriptWaiters: Map<CallId, TranscriptWaiter>;
   maxDurationTimers: Map<CallId, NodeJS.Timeout>;
 };
-

package/src/manager/events.ts

@@ -175,4 +175,3 @@ export function processEvent(ctx: CallManagerContext, event: NormalizedEvent): v
 
   persistCallRecord(ctx.storePath, call);
 }
-

package/src/manager/lookup.ts

@@ -31,4 +31,3 @@ export function findCall(params: {
     providerCallId: params.callIdOrProviderCallId,
   });
 }
-

package/src/manager/outbound.ts

@@ -68,7 +68,7 @@ export async function initiateCall(
     // For notify mode with a message, use inline TwiML with <Say>.
     let inlineTwiml: string | undefined;
     if (mode === "notify" && initialMessage) {
-      const pollyVoice = mapVoiceToPolly(ctx.config.tts.voice);
+      const pollyVoice = mapVoiceToPolly(ctx.config.tts?.openai?.voice);
       inlineTwiml = generateNotifyTwiml(initialMessage, pollyVoice);
       console.log(`[voice-call] Using inline TwiML for notify mode (voice: ${pollyVoice})`);
     }
@@ -120,11 +120,13 @@ export async function speak(
 
     addTranscriptEntry(call, "bot", text);
 
+    const voice =
+      ctx.provider?.name === "twilio" ? ctx.config.tts?.openai?.voice : undefined;
     await ctx.provider.playTts({
       callId,
       providerCallId: call.providerCallId,
       text,
-      voice: ctx.config.tts.voice,
+      voice,
     });
 
     return { success: true };
@@ -244,4 +246,3 @@ export async function endCall(
     return { success: false, error: err instanceof Error ? err.message : String(err) };
   }
 }
-

package/src/manager/state.ts

@@ -48,4 +48,3 @@ export function addTranscriptEntry(
   };
   call.transcript.push(entry);
 }
-

package/src/manager/store.ts

@@ -86,4 +86,3 @@ export async function getCallHistoryFromStore(
 
   return calls;
 }
-

package/src/manager/timers.ts

@@ -84,4 +84,3 @@ export function waitForFinalTranscript(
     ctx.transcriptWaiters.set(callId, { resolve, reject, timeout });
   });
 }
-

package/src/manager/twiml.ts

@@ -7,4 +7,3 @@ export function generateNotifyTwiml(message: string, voice: string): string {
   <Hangup/>
 </Response>`;
 }
-

package/src/manager.ts

@@ -143,7 +143,7 @@ export class CallManager {
       // For notify mode with a message, use inline TwiML with <Say>
       let inlineTwiml: string | undefined;
       if (mode === "notify" && initialMessage) {
-        const pollyVoice = mapVoiceToPolly(this.config.tts.voice);
+        const pollyVoice = mapVoiceToPolly(this.config.tts?.openai?.voice);
         inlineTwiml = this.generateNotifyTwiml(initialMessage, pollyVoice);
         console.log(
           `[voice-call] Using inline TwiML for notify mode (voice: ${pollyVoice})`,
@@ -210,11 +210,13 @@ export class CallManager {
       this.addTranscriptEntry(call, "bot", text);
 
       // Play TTS
+      const voice =
+        this.provider?.name === "twilio" ? this.config.tts?.openai?.voice : undefined;
       await this.provider.playTts({
         callId,
         providerCallId: call.providerCallId,
         text,
-        voice: this.config.tts.voice,
+        voice,
       });
 
       return { success: true };

package/src/media-stream.test.ts

@@ -0,0 +1,97 @@
+import { describe, expect, it } from "vitest";
+
+import type {
+  OpenAIRealtimeSTTProvider,
+  RealtimeSTTSession,
+} from "./providers/stt-openai-realtime.js";
+import { MediaStreamHandler } from "./media-stream.js";
+
+const createStubSession = (): RealtimeSTTSession => ({
+  connect: async () => {},
+  sendAudio: () => {},
+  waitForTranscript: async () => "",
+  onPartial: () => {},
+  onTranscript: () => {},
+  onSpeechStart: () => {},
+  close: () => {},
+  isConnected: () => true,
+});
+
+const createStubSttProvider = (): OpenAIRealtimeSTTProvider =>
+  ({
+    createSession: () => createStubSession(),
+  }) as unknown as OpenAIRealtimeSTTProvider;
+
+const flush = async (): Promise<void> => {
+  await new Promise((resolve) => setTimeout(resolve, 0));
+};
+
+const waitForAbort = (signal: AbortSignal): Promise<void> =>
+  new Promise((resolve) => {
+    if (signal.aborted) {
+      resolve();
+      return;
+    }
+    signal.addEventListener("abort", () => resolve(), { once: true });
+  });
+
+describe("MediaStreamHandler TTS queue", () => {
+  it("serializes TTS playback and resolves in order", async () => {
+    const handler = new MediaStreamHandler({
+      sttProvider: createStubSttProvider(),
+    });
+    const started: number[] = [];
+    const finished: number[] = [];
+
+    let resolveFirst!: () => void;
+    const firstGate = new Promise<void>((resolve) => {
+      resolveFirst = resolve;
+    });
+
+    const first = handler.queueTts("stream-1", async () => {
+      started.push(1);
+      await firstGate;
+      finished.push(1);
+    });
+    const second = handler.queueTts("stream-1", async () => {
+      started.push(2);
+      finished.push(2);
+    });
+
+    await flush();
+    expect(started).toEqual([1]);
+
+    resolveFirst();
+    await first;
+    await second;
+
+    expect(started).toEqual([1, 2]);
+    expect(finished).toEqual([1, 2]);
+  });
+
+  it("cancels active playback and clears queued items", async () => {
+    const handler = new MediaStreamHandler({
+      sttProvider: createStubSttProvider(),
+    });
+
+    let queuedRan = false;
+    const started: string[] = [];
+
+    const active = handler.queueTts("stream-1", async (signal) => {
+      started.push("active");
+      await waitForAbort(signal);
+    });
+    void handler.queueTts("stream-1", async () => {
+      queuedRan = true;
+    });
+
+    await flush();
+    expect(started).toEqual(["active"]);
+
+    handler.clearTtsQueue("stream-1");
+    await active;
+    await flush();
+
+    expect(queuedRan).toBe(false);
+  });
+});