par-cli-tts 0.4.1__tar.gz → 0.4.2__tar.gz

{par_cli_tts-0.4.1 → par_cli_tts-0.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: par-cli-tts
-Version: 0.4.1
+Version: 0.4.2
 Summary: PAR CLI TTS - Command line text-to-speech tool using ElevenLabs with voice caching and name resolution
 Project-URL: Homepage, https://github.com/paulrobello/par-cli-tts
 Project-URL: Documentation, https://github.com/paulrobello/par-cli-tts/blob/main/README.md
@@ -463,6 +463,10 @@ provider: kokoro-onnx
 # Default voice
 voice: Rachel
 
+# API keys (optional - can also be set via environment variables)
+# elevenlabs_api_key: your-elevenlabs-api-key-here
+# openai_api_key: your-openai-api-key-here
+
 # Output settings
 output_dir: ~/Documents/audio
 keep_temp: false

{par_cli_tts-0.4.1 → par_cli_tts-0.4.2}/README.md

@@ -400,6 +400,10 @@ provider: kokoro-onnx
 # Default voice
 voice: Rachel
 
+# API keys (optional - can also be set via environment variables)
+# elevenlabs_api_key: your-elevenlabs-api-key-here
+# openai_api_key: your-openai-api-key-here
+
 # Output settings
 output_dir: ~/Documents/audio
 keep_temp: false

{par_cli_tts-0.4.1 → par_cli_tts-0.4.2}/src/__init__.py

@@ -1,3 +1,3 @@
 """PAR CLI TTS - Command line text-to-speech tool."""
 
-__version__ = "0.4.1"
+__version__ = "0.4.2"

{par_cli_tts-0.4.1 → par_cli_tts-0.4.2}/src/config_file.py

@@ -18,6 +18,10 @@ class ConfigFile(BaseModel):
     voice: str | None = Field(None, description="Default voice")
     model: str | None = Field(None, description="Default model")
 
+    # API keys (optional - can also be set via environment variables)
+    elevenlabs_api_key: str | None = Field(None, description="ElevenLabs API key")
+    openai_api_key: str | None = Field(None, description="OpenAI API key")
+
     # Output settings
     output_dir: str | None = Field(None, description="Default output directory")
     output_format: str | None = Field(None, description="Default output format")
@@ -102,6 +106,10 @@ class ConfigManager:
             "# Default model",
             "# model: eleven_monolingual_v1",
             "",
+            "# API keys (optional - can also be set via environment variables)",
+            "# elevenlabs_api_key: your-elevenlabs-api-key-here",
+            "# openai_api_key: your-openai-api-key-here",
+            "",
             "# Output settings",
             "# output_dir: ~/Documents/audio",
             "# output_format: mp3",

{par_cli_tts-0.4.1 → par_cli_tts-0.4.2}/src/providers/elevenlabs.py

@@ -7,12 +7,14 @@ from typing import Any
 
 with warnings.catch_warnings():
     warnings.filterwarnings("ignore", message="Core Pydantic V1 functionality", category=UserWarning)
-    from elevenlabs import VoiceSettings, play, save
+    from elevenlabs import VoiceSettings
     from elevenlabs.client import ElevenLabs
+    from elevenlabs.play import save
 
 from src.defaults import DEFAULT_ELEVENLABS_VOICE
 from src.http_client import create_http_client
 from src.providers.base import TTSProvider, Voice
+from src.utils import play_audio_bytes
 from src.voice_cache import VoiceCache, resolve_voice_identifier
 
 
@@ -152,20 +154,14 @@ class ElevenLabsProvider(TTSProvider):
 
     def play_audio(self, audio_data: bytes | Iterator[bytes], volume: float = 1.0) -> None:
         """
-        Play audio data.
+        Play audio data with volume control.
 
         Args:
             audio_data: Audio data to play.
             volume: Volume level (0.0 = silent, 1.0 = normal, 2.0 = double volume).
-                   Note: ElevenLabs play() doesn't support volume, will use system default.
         """
-        # For play, we need to convert iterator to bytes
-        if isinstance(audio_data, bytes):
-            play(audio_data)
-        else:
-            # Convert iterator to bytes for playback
-            audio_bytes = b"".join(audio_data)
-            play(audio_bytes)
+        # Convert iterator to bytes if needed
+        if not isinstance(audio_data, bytes):
+            audio_data = b"".join(audio_data)
 
-        # Note: ElevenLabs play() function doesn't support volume control
-        # Consider using system players with volume support if needed
+        play_audio_bytes(audio_data, volume=volume, suffix=".mp3")

{par_cli_tts-0.4.1 → par_cli_tts-0.4.2}/src/tts_cli.py

@@ -28,48 +28,60 @@ from src.providers import PROVIDERS, TTSProvider
 app = typer.Typer(help="Text-to-speech command line tool with multiple provider support")
 
 
-def get_api_key(provider: str) -> str | None:
+def get_api_key(provider: str, config_file: Any = None) -> str | None:
     """
-    Get API key for the specified provider from environment.
+    Get API key for the specified provider from config file or environment.
 
     Args:
         provider: Provider name (elevenlabs, openai, kokoro-onnx).
+        config_file: Optional config file with API keys.
 
     Returns:
         API key string or None for providers that don't need one.
 
     Raises:
-        SystemExit: If API key is not found in environment.
+        SystemExit: If API key is not found anywhere.
     """
     # kokoro-onnx doesn't need an API key
     if provider == "kokoro-onnx":
         return None
 
-    env_var_map = {
-        "elevenlabs": "ELEVENLABS_API_KEY",
-        "openai": "OPENAI_API_KEY",
+    # Map provider to config file field and environment variable
+    key_map = {
+        "elevenlabs": ("elevenlabs_api_key", "ELEVENLABS_API_KEY"),
+        "openai": ("openai_api_key", "OPENAI_API_KEY"),
     }
 
-    env_var = env_var_map.get(provider)
-    if not env_var:
+    if provider not in key_map:
         handle_error(f"Unknown provider '{provider}'", ErrorType.INVALID_PROVIDER)
         return None  # For type checker, never reached
 
+    config_field, env_var = key_map[provider]
+
+    # Check config file first
+    if config_file:
+        api_key = getattr(config_file, config_field, None)
+        if api_key:
+            return api_key
+
+    # Fall back to environment variable
     api_key = os.getenv(env_var)
-    if not api_key and provider != "kokoro-onnx":
+    if not api_key:
         handle_error(
-            f"{env_var} not found. Please set {env_var} in your .env file or environment", ErrorType.MISSING_API_KEY
+            f"{env_var} not found. Please set {env_var} in your config file or environment",
+            ErrorType.MISSING_API_KEY,
         )
 
     return api_key
 
 
-def create_provider(provider_name: str, **kwargs: Any) -> TTSProvider:
+def create_provider(provider_name: str, config_file: Any = None, **kwargs: Any) -> TTSProvider:
     """
     Create a TTS provider instance.
 
     Args:
         provider_name: Name of the provider.
+        config_file: Optional config file with API keys.
         **kwargs: Additional provider configuration.
 
     Returns:
@@ -83,7 +95,7 @@ def create_provider(provider_name: str, **kwargs: Any) -> TTSProvider:
             f"Unknown provider '{provider_name}'. Available: {', '.join(PROVIDERS.keys())}", ErrorType.INVALID_PROVIDER
         )
 
-    api_key = get_api_key(provider_name)
+    api_key = get_api_key(provider_name, config_file)
     validate_api_key(api_key, provider_name)
     provider_class = PROVIDERS[provider_name]
 
@@ -477,7 +489,10 @@ def handle_speech_generation(
 
             if play_audio:
                 console.print("[cyan]Playing audio...[/cyan]")
-                tts_provider.play_audio(audio_data, volume=volume)
+                # Read from saved file since iterator was consumed
+                with open(output_path, "rb") as f:
+                    audio_bytes = f.read()
+                tts_provider.play_audio(audio_bytes, volume=volume)
         else:
             if play_audio:
                 console.print("[cyan]Playing audio...[/cyan]")
@@ -496,7 +511,10 @@ def handle_speech_generation(
                 tts_provider.save_audio(audio_data, tmp_path)
 
                 try:
-                    tts_provider.play_audio(audio_data, volume=volume)
+                    # Read from saved file since iterator was consumed
+                    with open(tmp_path, "rb") as f:
+                        audio_bytes = f.read()
+                    tts_provider.play_audio(audio_bytes, volume=volume)
 
                     if keep_temp or temp_dir:
                         console.print(f"[green]Audio saved to: {tmp_path}[/green]")
@@ -543,14 +561,14 @@ def main(
         str | None, typer.Argument(help="Text to convert to speech. Use '-' for stdin, '@filename' to read from file")
     ] = None,
     provider: Annotated[
-        str,
+        str | None,
         typer.Option(
             "-P",
             "--provider",
             help="TTS provider to use (elevenlabs, openai, kokoro-onnx)",
             envvar="TTS_PROVIDER",
         ),
-    ] = DEFAULT_PROVIDER,
+    ] = None,
     voice: Annotated[
         str | None,
         typer.Option(
@@ -754,7 +772,7 @@ def main(
 
     # Apply config file defaults (CLI args override these)
     if config_file:
-        provider = provider or config_file.provider or DEFAULT_PROVIDER
+        provider = provider or config_file.provider
         voice = voice or config_file.voice
         model = model or config_file.model
         output = output or (Path(config_file.output_dir) / "output.mp3" if config_file.output_dir else None)
@@ -771,6 +789,10 @@ def main(
         )
         debug = debug or config_file.debug or False
 
+    # Apply default provider if still not set
+    if not provider:
+        provider = DEFAULT_PROVIDER
+
     # Store debug mode globally for error handler
     sys._debug_mode = debug  # type: ignore
 
@@ -794,7 +816,7 @@ def main(
         return
 
     # Create provider
-    tts_provider = create_provider(provider)
+    tts_provider = create_provider(provider, config_file)
 
     # Handle cache management operations (ElevenLabs only)
     if refresh_cache or clear_cache_samples: