Skip to content

World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video production studio.

fix: scope fal providers and Google TTS networking

calesthiocffc18308f82
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"])