converse-framework 0.2.0__tar.gz → 0.2.2__tar.gz

{converse_framework-0.2.0 → converse_framework-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: converse-framework
-Version: 0.2.0
+Version: 0.2.2
 Summary: Provider-agnostic speech stack for speech-to-speech applications
 License: MIT
 License-File: LICENSE
@@ -49,6 +49,38 @@ Description-Content-Type: text/markdown
 
 Provider-agnostic speech stack for speech-to-speech applications.
 
+## Table of Contents
+
+- [Install](#install)
+  - [Missing dependency behavior](#missing-dependency-behavior)
+  - [Python version compatibility](#python-version-compatibility)
+- [Quick Start](#quick-start)
+  - [Provider status semantics](#provider-status-semantics)
+- [Recipes](#recipes)
+  - [Minimal mock text pipeline](#minimal-mock-text-pipeline)
+  - [Audio frame to utterance collector to pipeline](#audio-frame-to-utterance-collector-to-pipeline)
+  - [Custom provider registration](#custom-provider-registration)
+  - [Custom event sink](#custom-event-sink)
+  - [Browser playback](#browser-playback-js-reference-client)
+  - [Browser microphone capture](#browser-microphone-capture-js-reference-client)
+  - [Mobile browser microphone testing](#mobile-browser-microphone-testing)
+  - [Wrap an external CLI as a provider](#wrap-an-external-cli-as-a-provider)
+  - [Pocket TTS voice listing and configuration](#pocket-tts-voice-listing-and-configuration)
+  - [CUDA DLL helper](#cuda-dll-helper-windows)
+- [Runtime Provider Updates](#runtime-provider-updates)
+  - [ProviderBundle.replace()](#providerbundlereplace)
+  - [ProviderBundle.unload_replaced()](#providerbundleunload_replaced)
+  - [SpeechPipeline.update_providers()](#speechpipelineupdate_providers)
+  - [AudioUtteranceCollector.update_vad_provider()](#audioutterancecollectorupdate_vad_provider)
+  - [End-to-end pattern](#end-to-end-pattern)
+- [WebSocket Session Helper](#websocket-session-helper)
+- [Examples](#examples)
+  - [Text chat](#text-chat-automated-test-covered)
+  - [Voice chat](#voice-chat-manual)
+- [Framework / App Boundary](#framework--app-boundary)
+  - [Transport boundary](#transport-boundary)
+- [Status](#status)
+
 ## Install
 
 ```bash
@@ -644,7 +676,7 @@ for v in voices:
 Change voice (clears only the voice cache, preserves the loaded model):
 
 ```python
-result = provider.configure(voice="galileo")
+result = provider.configure(voice="anna")
 print(result.changed, result.requires_reload)
 # True, False — model stays, voice state reloaded
 ```

{converse_framework-0.2.0 → converse_framework-0.2.2}/README.md

@@ -2,6 +2,38 @@
 
 Provider-agnostic speech stack for speech-to-speech applications.
 
+## Table of Contents
+
+- [Install](#install)
+  - [Missing dependency behavior](#missing-dependency-behavior)
+  - [Python version compatibility](#python-version-compatibility)
+- [Quick Start](#quick-start)
+  - [Provider status semantics](#provider-status-semantics)
+- [Recipes](#recipes)
+  - [Minimal mock text pipeline](#minimal-mock-text-pipeline)
+  - [Audio frame to utterance collector to pipeline](#audio-frame-to-utterance-collector-to-pipeline)
+  - [Custom provider registration](#custom-provider-registration)
+  - [Custom event sink](#custom-event-sink)
+  - [Browser playback](#browser-playback-js-reference-client)
+  - [Browser microphone capture](#browser-microphone-capture-js-reference-client)
+  - [Mobile browser microphone testing](#mobile-browser-microphone-testing)
+  - [Wrap an external CLI as a provider](#wrap-an-external-cli-as-a-provider)
+  - [Pocket TTS voice listing and configuration](#pocket-tts-voice-listing-and-configuration)
+  - [CUDA DLL helper](#cuda-dll-helper-windows)
+- [Runtime Provider Updates](#runtime-provider-updates)
+  - [ProviderBundle.replace()](#providerbundlereplace)
+  - [ProviderBundle.unload_replaced()](#providerbundleunload_replaced)
+  - [SpeechPipeline.update_providers()](#speechpipelineupdate_providers)
+  - [AudioUtteranceCollector.update_vad_provider()](#audioutterancecollectorupdate_vad_provider)
+  - [End-to-end pattern](#end-to-end-pattern)
+- [WebSocket Session Helper](#websocket-session-helper)
+- [Examples](#examples)
+  - [Text chat](#text-chat-automated-test-covered)
+  - [Voice chat](#voice-chat-manual)
+- [Framework / App Boundary](#framework--app-boundary)
+  - [Transport boundary](#transport-boundary)
+- [Status](#status)
+
 ## Install
 
 ```bash
@@ -597,7 +629,7 @@ for v in voices:
 Change voice (clears only the voice cache, preserves the loaded model):
 
 ```python
-result = provider.configure(voice="galileo")
+result = provider.configure(voice="anna")
 print(result.changed, result.requires_reload)
 # True, False — model stays, voice state reloaded
 ```

{converse_framework-0.2.0 → converse_framework-0.2.2}/converse_framework/providers/pocket_tts.py

@@ -40,27 +40,32 @@ class PocketTTSProvider(TTSProvider):
         # Known voice identifiers for pocket-tts; listed here so status
         # can advertise them without importing the heavy backend.
         self._known_voices = (
+            {"id": "alba", "label": "Alba", "language": "en"},
+            {"id": "giovanni", "label": "Giovanni", "language": "it"},
+            {"id": "lola", "label": "Lola", "language": "es"},
+            {"id": "juergen", "label": "Juergen", "language": "de"},
+            {"id": "rafael", "label": "Rafael", "language": "pt"},
+            {"id": "estelle", "label": "Estelle", "language": "fr"},
+            {"id": "anna", "label": "Anna", "language": "en"},
             {"id": "azelma", "label": "Azelma", "language": "en"},
-            {"id": "bela", "label": "Bela", "language": "en"},
-            {"id": "conrad", "label": "Conrad", "language": "en"},
-            {"id": "demeter", "label": "Demeter", "language": "en"},
-            {"id": "ebenezer", "label": "Ebenezer", "language": "en"},
-            {"id": "ferdinand", "label": "Ferdinand", "language": "en"},
-            {"id": "gaspard", "label": "Gaspard", "language": "en"},
-            {"id": "horace", "label": "Horace", "language": "en"},
-            {"id": "ivo", "label": "Ivo", "language": "en"},
-            {"id": "jean", "label": "Jean", "language": "fr"},
-            {"id": "kimber", "label": "Kimber", "language": "en"},
-            {"id": "lobelia", "label": "Lobelia", "language": "en"},
-            {"id": "marie", "label": "Marie", "language": "fr"},
-            {"id": "nico", "label": "Nico", "language": "en"},
-            {"id": "orion", "label": "Orion", "language": "en"},
-            {"id": "pavel", "label": "Pavel", "language": "en"},
-            {"id": "quito", "label": "Quito", "language": "en"},
-            {"id": "river", "label": "River", "language": "en"},
-            {"id": "sophia", "label": "Sophia", "language": "en"},
-            {"id": "tom", "label": "Tom", "language": "en"},
-            {"id": "xavier", "label": "Xavier", "language": "en"},
+            {"id": "bill_boerst", "label": "Bill Boerst", "language": "en"},
+            {"id": "caro_davy", "label": "Caro Davy", "language": "en"},
+            {"id": "charles", "label": "Charles", "language": "en"},
+            {"id": "cosette", "label": "Cosette", "language": "en"},
+            {"id": "eponine", "label": "Eponine", "language": "en"},
+            {"id": "eve", "label": "Eve", "language": "en"},
+            {"id": "fantine", "label": "Fantine", "language": "en"},
+            {"id": "george", "label": "George", "language": "en"},
+            {"id": "jane", "label": "Jane", "language": "en"},
+            {"id": "jean", "label": "Jean", "language": "en"},
+            {"id": "javert", "label": "Javert", "language": "en"},
+            {"id": "marius", "label": "Marius", "language": "en"},
+            {"id": "mary", "label": "Mary", "language": "en"},
+            {"id": "michael", "label": "Michael", "language": "en"},
+            {"id": "paul", "label": "Paul", "language": "en"},
+            {"id": "peter_yearsley", "label": "Peter Yearsley", "language": "en"},
+            {"id": "stuart_bell", "label": "Stuart Bell", "language": "en"},
+            {"id": "vera", "label": "Vera", "language": "en"},
         )
 
     @property

{converse_framework-0.2.0 → converse_framework-0.2.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "converse-framework"
-version = "0.2.0"
+version = "0.2.2"
 description = "Provider-agnostic speech stack for speech-to-speech applications"
 readme = "README.md"
 license = { text = "MIT" }

{converse_framework-0.2.0 → converse_framework-0.2.2}/tests/test_providers.py

@@ -208,8 +208,8 @@ def test_pocket_tts_set_voice_clears_only_voice_state():
     assert provider._model is not None
     assert provider._voice_state is not None
 
-    result = provider.set_voice("bela")
-    assert result.active_voice == "bela"
+    result = provider.set_voice("anna")
+    assert result.active_voice == "anna"
     # Model stays loaded
     assert provider._model is not None
     # Voice state cleared
@@ -282,10 +282,10 @@ def test_pocket_tts_configure_voice_unloads_voice_state():
         ),
     )
 
-    result = asyncio.run(provider.configure(voice="bela"))
+    result = asyncio.run(provider.configure(voice="anna"))
     assert result.changed is True
     assert result.requires_reload is True
-    assert provider.voice == "bela"
+    assert provider.voice == "anna"
     assert provider._model is not None
     assert provider._voice_state is None
 
@@ -354,17 +354,50 @@ def test_pocket_tts_list_voices_returns_structured_voice_info():
     )
 
     voices = provider.list_voices()
-    assert len(voices) >= 3
+    expected_ids = [
+        "alba",
+        "giovanni",
+        "lola",
+        "juergen",
+        "rafael",
+        "estelle",
+        "anna",
+        "azelma",
+        "bill_boerst",
+        "caro_davy",
+        "charles",
+        "cosette",
+        "eponine",
+        "eve",
+        "fantine",
+        "george",
+        "jane",
+        "jean",
+        "javert",
+        "marius",
+        "mary",
+        "michael",
+        "paul",
+        "peter_yearsley",
+        "stuart_bell",
+        "vera",
+    ]
+    assert [v.id for v in voices] == expected_ids
     assert isinstance(voices[0], VoiceInfo)
-    assert voices[0].id == "azelma"
-    assert voices[0].label == "Azelma"
+    assert voices[0].id == "alba"
+    assert voices[0].label == "Alba"
 
     # Find a voice by id
     by_id = {v.id: v for v in voices}
-    assert "bela" in by_id
-    assert by_id["bela"].language == "en"
-    # French voices
-    assert by_id["jean"].language == "fr"
+    assert "anna" in by_id
+    assert by_id["anna"].language == "en"
+    # Multilingual voices
+    assert by_id["estelle"].language == "fr"
+    assert by_id["giovanni"].language == "it"
+    assert by_id["lola"].language == "es"
+    assert by_id["juergen"].language == "de"
+    assert by_id["rafael"].language == "pt"
+    assert by_id["jean"].language == "en"
     assert by_id["jean"].gender == "neutral"
 
 

{converse_framework-0.2.0 → converse_framework-0.2.2}/tests/test_session.py

@@ -226,10 +226,10 @@ async def test_settings_update_routes_to_hook():
     session = WebSocketSession(transport, hooks=hooks)  # type: ignore[arg-type]
 
     await session.handle_message(
-        {"type": "settings.update", "payload": {"voice": "bela"}}
+        {"type": "settings.update", "payload": {"voice": "anna"}}
     )
     assert len(settings_log) == 1
-    assert settings_log[0] == {"voice": "bela"}
+    assert settings_log[0] == {"voice": "anna"}
 
 
 @pytest.mark.asyncio
@@ -238,7 +238,7 @@ async def test_settings_update_no_hook_is_silent():
     session = WebSocketSession(transport)  # type: ignore[arg-type]
 
     await session.handle_message(
-        {"type": "settings.update", "payload": {"voice": "bela"}}
+        {"type": "settings.update", "payload": {"voice": "anna"}}
     )
     # No events — session silently ignores unhandled settings
     assert len(transport.sent) == 0