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.
Python agentagentic-aiaiclaudecopilotcursorelevenlabsffmpegfluximage-generationopen-sourceopenaipythonremotionstable-diffusiontext-to-speechtext-to-videovideo-generationvideo-production
fix: integrate Azure TTS with shared selector
calesthio078eb7eecdc9
diff --git a/tests/tools/test_azure_tts.py b/tests/tools/test_azure_tts.pyindex a863c67c..cdc1df7d 100644--- a/tests/tools/test_azure_tts.py+++ b/tests/tools/test_azure_tts.py@@ -6,6 +6,7 @@ construction, and execute() guardrails."""import sys+import xml.etree.ElementTree as ETfrom pathlib import Pathimport pytest@@ -148,6 +149,20 @@ class TestSSML:ssml = t._build_ssml({"text": "Hallo", "locale": "de-DE"}, "de-DE-KatjaNeural")assert 'xml:lang="de-DE"' in ssml+ def test_ssml_quotes_in_attributes_remain_well_formed(self):+ t = AzureTTS()+ ssml = t._build_ssml(+ {+ "text": 'She said "hello" & waved',+ "locale": 'en-US" data-bad="yes',+ "rate": '0%" data-bad="yes',+ "style": 'calm" data-bad="yes',+ },+ 'en-US-GuyNeural" data-bad="yes',+ )+ root = ET.fromstring(ssml)+ assert all("data-bad" not in element.attrib for element in root.iter())+def test_host_prefers_explicit_endpoint(self, monkeypatch):monkeypatch.setenv("AZURE_TTS_ENDPOINT", "https://custom.tts.example.com/")assert AzureTTS()._host() == "https://custom.tts.example.com"@@ -201,6 +216,39 @@ class TestExecute:assert captured["headers"]["X-Microsoft-OutputFormat"] == "audio-48khz-192kbitrate-mono-mp3"assert b"Hello world" in captured["body"]+ def test_selector_adapts_shared_controls_for_azure(self, azure_env, tmp_path, monkeypatch):+ import requests+ from tools.audio.tts_selector import TTSSelector++ captured = {}++ def fake_post(url, headers=None, data=None, timeout=None):+ captured["body"] = data.decode("utf-8")+ return _FakeResponse()++ monkeypatch.setattr(requests, "post", fake_post)+ monkeypatch.setattr(TTSSelector, "_providers", lambda self: [AzureTTS()])++ result = TTSSelector().execute(+ {+ "text": "Selector narration",+ "preferred_provider": "azure",+ "voice_id": "jenny",+ "speaking_rate": 1.1,+ "pitch": 2,+ "style": 0.8,+ "output_format": "mp3_44100_128",+ "output_path": str(tmp_path / "selector.mp3"),+ }+ )++ assert result.success+ assert result.data["selected_tool"] == "azure_tts"+ assert result.data["voice"] == "en-US-JennyNeural"+ assert 'rate="+10%"' in captured["body"]+ assert 'pitch="+2st"' in captured["body"]+ assert "express-as" not in captured["body"]+def test_wav_output_format(self, azure_env, tmp_path, monkeypatch):import requestsdiff --git a/tools/audio/azure_tts.py b/tools/audio/azure_tts.pyindex 6943fed6..220dffc2 100644--- a/tools/audio/azure_tts.py+++ b/tools/audio/azure_tts.py@@ -19,7 +19,7 @@ import osimport timefrom pathlib import Pathfrom typing import Any-from xml.sax.saxutils import escape+from xml.sax.saxutils import escape, quoteattrfrom tools.base_tool import (BaseTool,@@ -201,23 +201,21 @@ class AzureTTS(BaseTool):return self.RECOMMENDED_VOICES.get(voice.lower(), voice)def _build_ssml(self, inputs: dict[str, Any], voice: str) -> str:- locale = inputs.get("locale", "en-US")- rate = inputs.get("rate", "0%")- pitch = inputs.get("pitch", "0%")+ locale = str(inputs.get("locale", "en-US"))+ rate = str(inputs.get("rate", "0%"))+ pitch = str(inputs.get("pitch", "0%"))style = inputs.get("style")text = escape(inputs["text"])- inner = f'<prosody rate="{escape(rate)}" pitch="{escape(pitch)}">{text}</prosody>'+ inner = f"<prosody rate={quoteattr(rate)} pitch={quoteattr(pitch)}>{text}</prosody>"if style:- inner = (- f'<mstts:express-as style="{escape(style)}">{inner}</mstts:express-as>'- )+ inner = f"<mstts:express-as style={quoteattr(str(style))}>{inner}</mstts:express-as>"return (f'<speak version="1.0" 'f'xmlns="http://www.w3.org/2001/10/synthesis" 'f'xmlns:mstts="https://www.w3.org/2001/mstts" '- f'xml:lang="{locale}">'- f'<voice name="{voice}">{inner}</voice></speak>'+ f"xml:lang={quoteattr(locale)}>"+ f"<voice name={quoteattr(voice)}>{inner}</voice></speak>")def execute(self, inputs: dict[str, Any]) -> ToolResult:diff --git a/tools/audio/tts_selector.py b/tools/audio/tts_selector.pyindex 5c20cd57..614b4bac 100644--- a/tools/audio/tts_selector.py+++ b/tools/audio/tts_selector.py@@ -188,7 +188,7 @@ class TTSSelector(BaseTool):if tool is None:return ToolResult(success=False, error="No TTS provider available.")- result = tool.execute(inputs)+ result = tool.execute(self._adapt_inputs(tool, inputs))if result.success:result.data.setdefault("selected_tool", tool.name)result.data["selected_provider"] = tool.provider@@ -202,6 +202,37 @@ class TTSSelector(BaseTool):]return result+ @staticmethod+ def _adapt_inputs(tool: BaseTool, inputs: dict[str, Any]) -> dict[str, Any]:+ """Translate capability-level controls to provider-native inputs."""+ adapted = dict(inputs)+ if tool.name != "azure_tts":+ return adapted++ if inputs.get("voice_id") and not inputs.get("voice"):+ adapted["voice"] = inputs["voice_id"]++ speed = inputs.get("speaking_rate", inputs.get("speed"))+ if speed is not None and "rate" not in inputs:+ percent = round((float(speed) - 1.0) * 100)+ adapted["rate"] = f"{percent:+d}%" if percent else "0%"++ pitch = inputs.get("pitch")+ if isinstance(pitch, (int, float)):+ adapted["pitch"] = f"{pitch:+g}st" if pitch else "0%"++ # The selector's numeric style is ElevenLabs-specific. Azure's style+ # is a named express-as value such as "calm" or "newscast".+ if not isinstance(inputs.get("style"), str):+ adapted.pop("style", None)++ output_format = str(inputs.get("output_format", ""))+ if output_format.startswith("mp3"):+ adapted["output_format"] = "mp3"+ elif output_format.startswith(("wav", "riff", "pcm")):+ adapted["output_format"] = "wav"+ return adapted+def _select_best_tool(self,inputs: dict[str, Any],