diff --git a/docs/PROVIDERS.md b/docs/PROVIDERS.md
index 7ad51bad..284c9e87 100644
--- a/docs/PROVIDERS.md
+++ b/docs/PROVIDERS.md
@@ -192,7 +192,7 @@ The ASR tool (`qwen3-asr-flash-filetrans`) uses an async submit-poll pattern. Au
 
 > **Broad single-key coverage.** One API key unlocks image and video providers across multiple models.
 
-**Tools unlocked:** `flux_image`, `recraft_image`, `kling_video`, `veo_video`, `minimax_video`
+**Tools unlocked:** `flux_image`, `recraft_image`, `kling_video`, `veo_video`, `minimax_video`, `fal_elevenlabs_tts`, `fal_elevenlabs_music`
 **Env var:** `FAL_KEY`
 
 #### Setup
@@ -225,6 +225,10 @@ No subscription — pure pay-as-you-go, no minimum spend.
 
 **Free tier:** None — but $0 to start, you only pay for what you use.
 
+The same key can also access ElevenLabs speech and music through fal.ai. Use
+`fal_elevenlabs_tts` when direct ElevenLabs credentials are unavailable, or
+select it through `tts_selector` with `preferred_provider: "fal.ai"`.
+
 ---
 
 ### Kling Official — Direct API
diff --git a/tests/tools/test_fal_elevenlabs_tts.py b/tests/tools/test_fal_elevenlabs_tts.py
index 81b2987c..e05c206f 100644
--- a/tests/tools/test_fal_elevenlabs_tts.py
+++ b/tests/tools/test_fal_elevenlabs_tts.py
@@ -37,6 +37,32 @@ def test_registry_discovers_fal_tts(monkeypatch):
     assert tool.get_status() == ToolStatus.AVAILABLE
 
 
+def test_tts_selector_routes_to_fal_provider(monkeypatch):
+    from tools.audio.tts_selector import TTSSelector
+    from tools.base_tool import ToolResult
+
+    monkeypatch.setenv("FAL_KEY", "test-key")
+    tool = FalElevenLabsTTS()
+    selector = TTSSelector()
+    monkeypatch.setattr(selector, "_providers", lambda: [tool])
+    monkeypatch.setattr(
+        selector,
+        "_select_best_tool",
+        lambda _inputs, _candidates, _context: (tool, None),
+    )
+    monkeypatch.setattr(
+        tool,
+        "execute",
+        lambda inputs: ToolResult(success=True, data={"received": inputs}),
+    )
+    result = selector.execute(
+        {"text": "hello", "preferred_provider": "fal.ai", "voice_id": "Rachel"}
+    )
+    assert result.success
+    assert result.data["selected_tool"] == "fal_elevenlabs_tts"
+    assert result.data["selected_provider"] == "fal.ai"
+
+
 def test_execute_submits_once_and_downloads_audio(tmp_path, monkeypatch):
     monkeypatch.setenv("FAL_KEY", "test-key")
     output_path = tmp_path / "speech.mp3"
diff --git a/tests/tools/test_google_tts_scoped_key.py b/tests/tools/test_google_tts_scoped_key.py
index 36ea45ac..fbc15af2 100644
--- a/tests/tools/test_google_tts_scoped_key.py
+++ b/tests/tools/test_google_tts_scoped_key.py
@@ -34,26 +34,3 @@ def test_tts_key_uses_header_and_is_redacted_from_errors(monkeypatch, tmp_path):
     assert result.success is False
     assert secret not in result.error
     assert "[REDACTED]" in result.error
-
-
-def test_production_adapter_can_force_google_tts_to_ipv4(monkeypatch, tmp_path):
-    import socket
-
-    import requests
-    import urllib3.util.connection
-
-    monkeypatch.setenv("GOOGLE_TTS_API_KEY", "test-key")
-    monkeypatch.setenv("GOOGLE_TTS_FORCE_IPV4", "1")
-    original = urllib3.util.connection.allowed_gai_family
-
-    def inspect_request(url, **kwargs):
-        assert urllib3.util.connection.allowed_gai_family() == socket.AF_INET
-        raise requests.HTTPError("safe expected failure")
-
-    monkeypatch.setattr(requests, "post", inspect_request)
-    result = GoogleTTS().execute(
-        {"text": "safe test sentence", "output_path": str(tmp_path / "speech.mp3")}
-    )
-
-    assert result.success is False
-    assert urllib3.util.connection.allowed_gai_family is original
diff --git a/tools/audio/google_tts.py b/tools/audio/google_tts.py
index 67fcbb97..f47dd4d6 100644
--- a/tools/audio/google_tts.py
+++ b/tools/audio/google_tts.py
@@ -8,10 +8,7 @@ from __future__ import annotations
 
 import base64
 import os
-import socket
-import threading
 import time
-from contextlib import contextmanager
 from pathlib import Path
 from typing import Any
 
@@ -33,32 +30,6 @@ from tools.google_credentials import (
 )
 
 
-_IPV4_REQUEST_LOCK = threading.Lock()
-
-
-@contextmanager
-def _google_tts_network_family():
-    """Use IPv4 when the deployment key is restricted to the server's IPv4."""
-    force_ipv4 = os.environ.get("GOOGLE_TTS_FORCE_IPV4", "").lower() in {
-        "1",
-        "true",
-        "yes",
-    }
-    if not force_ipv4:
-        yield
-        return
-
-    import urllib3.util.connection
-
-    with _IPV4_REQUEST_LOCK:
-        original = urllib3.util.connection.allowed_gai_family
-        urllib3.util.connection.allowed_gai_family = lambda: socket.AF_INET
-        try:
-            yield
-        finally:
-            urllib3.util.connection.allowed_gai_family = original
-
-
 class GoogleTTS(BaseTool):
     name = "google_tts"
     version = "0.1.0"
@@ -76,7 +47,6 @@ class GoogleTTS(BaseTool):
         "  GOOGLE_API_KEY or GEMINI_API_KEY remain supported for broader Google setups.\n"
         "  Google Cloud API key with Text-to-Speech enabled.\n"
         "  Enable the API at https://console.cloud.google.com/apis/library/texttospeech.googleapis.com\n"
-        "  Set GOOGLE_TTS_FORCE_IPV4=1 only when the key is restricted to the caller's IPv4.\n"
         "Auth option B — service account: set GOOGLE_APPLICATION_CREDENTIALS to the\n"
         "  path of a service-account JSON key (needs the 'google-auth' package)."
     )
@@ -309,13 +279,12 @@ class GoogleTTS(BaseTool):
         elif api_key:
             headers["x-goog-api-key"] = api_key
 
-        with _google_tts_network_family():
-            response = requests.post(
-                url,
-                headers=headers,
-                json=payload,
-                timeout=120,
-            )
+        response = requests.post(
+            url,
+            headers=headers,
+            json=payload,
+            timeout=120,
+        )
         response.raise_for_status()
 
         audio_content = base64.b64decode(response.json()["audioContent"])