Merge pull request #43 from OHF-Voice/synesthesiam-20250619-tts-streaming

1.7.0

Author: synesthesiam

.github/workflows/test.yml

@@ -17,13 +17,13 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python_version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python_version: ["3.8", "3.9", "3.10", "3.11", "3.12", "3.13"]
     steps:
       - uses: actions/checkout@v4.1.1
       - uses: actions/setup-python@v5
         with:
           python-version: "${{ matrix.python_version }}"
           cache: "pip"
           cache-dependency-path: pyproject.toml
-      - run: script/setup --dev
+      - run: script/setup --dev --http --zeroconf
       - run: script/test

CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## 1.7.0
+
+- Add streaming to `tts`, `handle`, and `asr`
+- Add `context` to more events
+- Add more tests
+
+## 1.6.2
+
+- Fix http requirements
+- Add missing http conf files
+
 ## 1.6.1
 
 - Migrate to pyproject.toml

README.md

@@ -91,6 +91,7 @@ Describe available services.
             * `installed` - true if currently installed (bool, required)
             * `description` - human-readable description (string, optional)
             * `version` - version of the model (string, optional)
+        * `supports_transcript_streaming` - true if program can stream transcript chunks
     * `tts` - list text to speech services (optional)
         * `models` - list of available models
             * `name` - unique name (required)
@@ -103,6 +104,7 @@ Describe available services.
             * `installed` - true if currently installed (bool, required)
             * `description` - human-readable description (string, optional)
             * `version` - version of the model (string, optional)
+       * `supports_synthesize_streaming` - true if program can stream text chunks
     * `wake` - list wake word detection services( optional )
         * `models` - list of available models (required)
             * `name` - unique name (required)
@@ -123,6 +125,7 @@ Describe available services.
             * `installed` - true if currently installed (bool, required)
             * `description` - human-readable description (string, optional)
             * `version` - version of the model (string, optional)
+        * `supports_handled_streaming` - true if program can stream response chunks
     * `intent` - list intent recognition services (optional)
         * `models` - list of available models (required)
             * `name` - unique name (required)
@@ -160,8 +163,19 @@ Transcribe audio into text.
     * `context` - context from previous interactions (object, optional)
 * `transcript` - response with transcription
     * `text` - text transcription of spoken audio (string, required)
+    * `language` - language of transcript (string, optional)
     * `context` - context for next interaction (object, optional)
 
+Streaming:
+
+1. `transcript-start` - starts stream
+    * `language` - language of transcript (string, optional)
+    * `context` - context from previous interactions (object, optional)
+2. `transcript-chunk`
+    * `text` - part of transcript (string, required)
+3. Original `transcript` event must be sent for backwards compatibility
+4. `transcript-stop` - end of stream
+
 ### Text to Speech
 
 Synthesize audio from text.
@@ -172,6 +186,20 @@ Synthesize audio from text.
         * `name` - name of voice (string, optional)
         * `language` - language of voice (string, optional)
         * `speaker` - speaker of voice (string, optional)
+        
+Streaming:
+
+1. `synthesize-start` - starts stream
+    * `context` - context from previous interactions (object, optional)
+    * `voice` - use a specific voice (optional)
+        * `name` - name of voice (string, optional)
+        * `language` - language of voice (string, optional)
+        * `speaker` - speaker of voice (string, optional)
+2. `synthesize-chunk`
+    * `text` - part of text to synthesize (string, required)
+3. Original `synthesize` message must be sent for backwards compatibility
+4. `synthesize-stop` - end of stream, final audio must be sent
+5. `synthesize-stopped` - sent back to server after final audio
 
 ### Wake Word
 
@@ -222,6 +250,15 @@ Handle structured intents or text directly.
     * `text` - response for user (string, optional)
     * `context` - context for next interactions (object, optional)
 
+Streaming:
+
+1. `handled-start` - starts stream
+    * `context` - context from previous interactions (object, optional)
+2. `handled-chunk`
+    * `text` - part of response (string, required)
+3. Original `handled` message must be sent for backwards compatibility
+4. `handled-stop` - end of stream
+
 ### Audio Output
 
 Play audio stream.
@@ -295,8 +332,23 @@ Pipelines are run on the server, but can be triggered remotely from the server a
 3. → `audio-chunk` (required)
     * Send audio chunks until silence is detected
 4. → `audio-stop` (required)
-5. ← `transcript`
+5. ← `transcript` (required)
     * Contains text transcription of spoken audio
+    
+Streaming:
+
+1. → `transcribe` event (optional)
+2. → `audio-start` (required)
+3. → `audio-chunk` (required)
+    * Send audio chunks until silence is detected
+4. ← `transcript-start` (required)
+5. ← `transcript-chunk` (required)
+    * Send transcript chunks as they're produced
+6. → `audio-stop` (required)
+7. ← `transcript` (required)
+    * Sent for backwards compatibility
+8. ← `transcript-stop` (required)
+
 
 ### Text to Speech
 
@@ -306,6 +358,22 @@ Pipelines are run on the server, but can be triggered remotely from the server a
     * One or more audio chunks
 4. ← `audio-stop`
 
+Streaming:
+
+1. → `synthesize-start` event (required)
+3. → `synthesize-chunk` event (required)
+    * Text chunks are sent as they're produced
+3. ← `audio-start`, `audio-chunk` (one or more), `audio-stop`
+    * Audio chunks are sent as they're produced with start/stop
+4. → `synthesize` event
+    * Sent for backwards compatibility
+5. → `synthesize-stop` event
+    * End of text stream
+6. ← Final audio must be sent
+    * `audio-start`, `audio-chunk` (one or more), `audio-stop`
+7. ← `synthesize-stopped`
+    * Tells server that final audio has been sent
+
 ### Wake Word Detection
 
 1. → `detect` event with `names` of wake words to detect (optional)
@@ -348,6 +416,16 @@ For text only:
 2. ← `handled` if successful
 3. ← `not-handled` if not successful
 
+Streaming text only (successful):
+
+1. → `transcript` with `text` to handle (required)
+2. ← `handled-start` (required)
+3. ← `handled-chunk` (required)
+    * Chunk of response text
+4. ← `handled` (required)
+    * Sent for backwards compatibility
+5. ← `handled-stop` (required)
+    
 ### Audio Output
 
 1. → `audio-start` (required)

pylintrc

@@ -31,7 +31,8 @@ disable=
   missing-class-docstring,
   missing-function-docstring,
   import-error,
-  consider-using-with
+  consider-using-with,
+  too-many-positional-arguments
 
 [FORMAT]
 expected-line-ending-format=LF

pyproject.toml

@@ -1,9 +1,9 @@
 [project]
 name = "wyoming"
-version = "1.6.2"
+version = "1.7.0"
 description = "Peer-to-peer protocol for voice assistants"
 readme = "README.md"
-requires-python = ">=3.8.1,<3.13"
+requires-python = ">=3.8.1,<3.14"
 license = {text = "MIT"}
 authors = [
     {name = "Michael Hansen", email = "mike@rhasspy.org"}
@@ -18,6 +18,7 @@ classifiers = [
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
     "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
 ]
 
 [project.urls]

script/format

@@ -9,10 +9,11 @@ _VENV_DIR = _PROGRAM_DIR / ".venv"
 _MODULE_DIR = _PROGRAM_DIR / "wyoming"
 _TESTS_DIR = _PROGRAM_DIR / "tests"
 
-context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
-subprocess.check_call(
-    [context.env_exe, "-m", "black", str(_MODULE_DIR), str(_TESTS_DIR)]
-)
-subprocess.check_call(
-    [context.env_exe, "-m", "isort", str(_MODULE_DIR), str(_TESTS_DIR)]
-)
+if _VENV_DIR.exists():
+    context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
+    python_exe = context.env_exe
+else:
+    python_exe = "python3"
+
+subprocess.check_call([python_exe, "-m", "black", str(_MODULE_DIR), str(_TESTS_DIR)])
+subprocess.check_call([python_exe, "-m", "isort", str(_MODULE_DIR), str(_TESTS_DIR)])

script/lint

@@ -9,19 +9,18 @@ _VENV_DIR = _PROGRAM_DIR / ".venv"
 _MODULE_DIR = _PROGRAM_DIR / "wyoming"
 _TESTS_DIR = _PROGRAM_DIR / "tests"
 
-context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
-subprocess.check_call(
-    [context.env_exe, "-m", "black", str(_MODULE_DIR), str(_TESTS_DIR), "--check"]
-)
-subprocess.check_call(
-    [context.env_exe, "-m", "isort", str(_MODULE_DIR), str(_TESTS_DIR), "--check"]
-)
-subprocess.check_call(
-    [context.env_exe, "-m", "flake8", str(_MODULE_DIR), str(_TESTS_DIR)]
-)
+if _VENV_DIR.exists():
+    context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
+    python_exe = context.env_exe
+else:
+    python_exe = "python3"
+
 subprocess.check_call(
-    [context.env_exe, "-m", "pylint", str(_MODULE_DIR), str(_TESTS_DIR)]
+    [python_exe, "-m", "black", str(_MODULE_DIR), str(_TESTS_DIR), "--check"]
 )
 subprocess.check_call(
-    [context.env_exe, "-m", "mypy", str(_MODULE_DIR), str(_TESTS_DIR)]
+    [python_exe, "-m", "isort", str(_MODULE_DIR), str(_TESTS_DIR), "--check"]
 )
+subprocess.check_call([python_exe, "-m", "flake8", str(_MODULE_DIR), str(_TESTS_DIR)])
+subprocess.check_call([python_exe, "-m", "pylint", str(_MODULE_DIR), str(_TESTS_DIR)])
+subprocess.check_call([python_exe, "-m", "mypy", str(_MODULE_DIR), str(_TESTS_DIR)])

script/package

@@ -7,7 +7,10 @@ _DIR = Path(__file__).parent
 _PROGRAM_DIR = _DIR.parent
 _VENV_DIR = _PROGRAM_DIR / ".venv"
 
-context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
-subprocess.check_call(
-    [context.env_exe, "-m", "build", "--wheel", "--sdist"]
-)
+if _VENV_DIR.exists():
+    context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
+    python_exe = context.env_exe
+else:
+    python_exe = "python3"
+
+subprocess.check_call([python_exe, "-m", "build", "--wheel", "--sdist"])

script/test

@@ -9,5 +9,10 @@ _PROGRAM_DIR = _DIR.parent
 _VENV_DIR = _PROGRAM_DIR / ".venv"
 _TEST_DIR = _PROGRAM_DIR / "tests"
 
-context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
-subprocess.check_call([context.env_exe, "-m", "pytest", _TEST_DIR] + sys.argv[1:])
+if _VENV_DIR.exists():
+    context = venv.EnvBuilder().ensure_directories(_VENV_DIR)
+    python_exe = context.env_exe
+else:
+    python_exe = "python3"
+
+subprocess.check_call([python_exe, "-m", "pytest", _TEST_DIR] + sys.argv[1:])

tests/test_audio.py

@@ -1,4 +1,5 @@
 """Test audio utilities."""
+
 import io
 import wave