@weirdfingers/baseboards 0.9.6 → 0.9.7

package/templates/api/src/boards/generators/implementations/fal/audio/beatoven_music_generation.py

@@ -1,171 +0,0 @@
-"""
-Beatoven music generation - royalty-free instrumental music generator.
-
-Generate high-quality instrumental music from electronic, hip hop, and indie rock
-to cinematic and classical genres. Designed for games, films, social content,
-podcasts, and similar applications.
-
-Based on Fal AI's beatoven/music-generation model.
-See: https://fal.ai/models/beatoven/music-generation
-"""
-
-import os
-
-from pydantic import BaseModel, Field
-
-from ....base import BaseGenerator, GeneratorExecutionContext, GeneratorResult
-
-
-class BeatovenMusicGenerationInput(BaseModel):
-    """Input schema for beatoven music generation.
-
-    All fields use appropriate types and validation based on the Fal AI API.
-    """
-
-    prompt: str = Field(
-        description="Text description of the desired music (style, mood, instruments, tempo, etc.)"
-    )
-    duration: float = Field(
-        default=90,
-        ge=5,
-        le=150,
-        description="Duration of generated music in seconds (5-150)",
-    )
-    refinement: int = Field(
-        default=100,
-        ge=10,
-        le=200,
-        description="Quality improvement level (10-200, higher is better quality)",
-    )
-    creativity: float = Field(
-        default=16,
-        ge=1,
-        le=20,
-        description="Creative interpretation degree (1-20, higher is more creative)",
-    )
-    seed: int | None = Field(
-        default=None,
-        ge=0,
-        le=2147483647,
-        description="Seed for reproducible results (0-2147483647, null for random)",
-    )
-    negative_prompt: str = Field(
-        default="",
-        description="Elements to exclude from the generated music",
-    )
-
-
-class FalBeatovenMusicGenerationGenerator(BaseGenerator):
-    """Beatoven music generation using fal.ai."""
-
-    name = "beatoven-music-generation"
-    artifact_type = "audio"
-    description = "Fal: Beatoven - generate royalty-free instrumental music from text prompts"
-
-    def get_input_schema(self) -> type[BeatovenMusicGenerationInput]:
-        return BeatovenMusicGenerationInput
-
-    async def generate(
-        self, inputs: BeatovenMusicGenerationInput, context: GeneratorExecutionContext
-    ) -> GeneratorResult:
-        """Generate music using fal.ai beatoven/music-generation model."""
-        # Check for API key (fal-client uses FAL_KEY environment variable)
-        if not os.getenv("FAL_KEY"):
-            raise ValueError("API configuration invalid. Missing FAL_KEY environment variable")
-
-        # Import fal_client
-        try:
-            import fal_client
-        except ImportError as e:
-            raise ImportError(
-                "fal.ai SDK is required for FalBeatovenMusicGenerationGenerator. "
-                "Install with: pip install weirdfingers-boards[generators-fal]"
-            ) from e
-
-        # Prepare arguments for fal.ai API
-        from typing import Any
-
-        arguments: dict[str, Any] = {
-            "prompt": inputs.prompt,
-            "duration": inputs.duration,
-            "refinement": inputs.refinement,
-            "creativity": inputs.creativity,
-        }
-
-        # Add optional parameters if provided
-        if inputs.seed is not None:
-            arguments["seed"] = inputs.seed
-
-        if inputs.negative_prompt:
-            arguments["negative_prompt"] = inputs.negative_prompt
-
-        # Submit async job and get handler
-        handler = await fal_client.submit_async(
-            "beatoven/music-generation",
-            arguments=arguments,
-        )
-
-        # Store the external job ID for tracking
-        await context.set_external_job_id(handler.request_id)
-
-        # Stream progress updates (sample every 3rd event to avoid spam)
-        from .....progress.models import ProgressUpdate
-
-        event_count = 0
-        async for event in handler.iter_events(with_logs=True):
-            event_count += 1
-
-            # Process every 3rd event to provide feedback without overwhelming
-            if event_count % 3 == 0:
-                # Extract logs if available
-                logs = getattr(event, "logs", None)
-                if logs:
-                    # Join log entries into a single message
-                    if isinstance(logs, list):
-                        message = " | ".join(str(log) for log in logs if log)
-                    else:
-                        message = str(logs)
-
-                    if message:
-                        await context.publish_progress(
-                            ProgressUpdate(
-                                job_id=handler.request_id,
-                                status="processing",
-                                progress=50.0,  # Approximate mid-point progress
-                                phase="processing",
-                                message=message,
-                            )
-                        )
-
-        # Get final result
-        result = await handler.get()
-
-        # Extract audio from result
-        # fal.ai returns: {"audio": {"url": "...", "content_type": "...", "file_size": ...}}
-        audio_data = result.get("audio")
-        if not audio_data:
-            raise ValueError("No audio returned from fal.ai API")
-
-        audio_url = audio_data.get("url")
-        if not audio_url:
-            raise ValueError("Audio missing URL in fal.ai response")
-
-        # Beatoven returns WAV format
-        audio_format = "wav"
-
-        # Store audio result
-        artifact = await context.store_audio_result(
-            storage_url=audio_url,
-            format=audio_format,
-            output_index=0,
-        )
-
-        return GeneratorResult(outputs=[artifact])
-
-    async def estimate_cost(self, inputs: BeatovenMusicGenerationInput) -> float:
-        """Estimate cost for beatoven music generation.
-
-        Estimated at approximately $0.05 per music generation.
-        Actual cost may vary based on duration and quality settings.
-        """
-        return 0.05  # $0.05 per music generation

package/templates/api/src/boards/generators/implementations/fal/audio/beatoven_sound_effect_generation.py

@@ -1,167 +0,0 @@
-"""
-fal.ai beatoven/sound-effect-generation generator.
-
-Create professional-grade sound effects from animal and vehicle to nature, sci-fi,
-and otherworldly sounds. Perfect for films, games, and digital content.
-
-Based on Fal AI's beatoven/sound-effect-generation model.
-See: https://fal.ai/models/beatoven/sound-effect-generation
-"""
-
-import os
-
-from pydantic import BaseModel, Field
-
-from ....base import BaseGenerator, GeneratorExecutionContext, GeneratorResult
-
-
-class BeatovenSoundEffectGenerationInput(BaseModel):
-    """Input schema for beatoven/sound-effect-generation.
-
-    Artifact fields are automatically detected via type introspection
-    and resolved from generation IDs to artifact objects.
-    """
-
-    prompt: str = Field(description="Describe the sound effect you want to generate")
-    duration: float = Field(
-        default=5,
-        ge=1,
-        le=35,
-        description="Length of the generated sound effect in seconds",
-    )
-    refinement: int = Field(
-        default=40,
-        ge=10,
-        le=200,
-        description="Refinement level - Higher values may improve quality but take longer",
-    )
-    creativity: float = Field(
-        default=16,
-        ge=1,
-        le=20,
-        description="Creativity level - higher values allow more creative interpretation",
-    )
-    negative_prompt: str = Field(
-        default="",
-        description="Describe the types of sounds you don't want to generate",
-    )
-    seed: int | None = Field(
-        default=None,
-        ge=0,
-        le=2147483647,
-        description="Random seed for reproducible results - leave empty for random generation",
-    )
-
-
-class FalBeatovenSoundEffectGenerationGenerator(BaseGenerator):
-    """Generator for creating professional-grade sound effects."""
-
-    name = "fal-beatoven-sound-effect-generation"
-    description = (
-        "Fal: Beatoven Sound Effects - create professional-grade sound effects "
-        "for films, games, and digital content"
-    )
-    artifact_type = "audio"
-
-    def get_input_schema(self) -> type[BeatovenSoundEffectGenerationInput]:
-        """Return the input schema for this generator."""
-        return BeatovenSoundEffectGenerationInput
-
-    async def generate(
-        self, inputs: BeatovenSoundEffectGenerationInput, context: GeneratorExecutionContext
-    ) -> GeneratorResult:
-        """Generate audio using fal.ai beatoven/sound-effect-generation."""
-        # Check for API key
-        if not os.getenv("FAL_KEY"):
-            raise ValueError("API configuration invalid. Missing FAL_KEY environment variable")
-
-        # Import fal_client
-        try:
-            import fal_client
-        except ImportError as e:
-            raise ImportError(
-                "fal.ai SDK is required for FalBeatovenSoundEffectGenerationGenerator. "
-                "Install with: pip install weirdfingers-boards[generators-fal]"
-            ) from e
-
-        # Prepare arguments for fal.ai API
-        from typing import Any
-
-        arguments: dict[str, Any] = {
-            "prompt": inputs.prompt,
-            "duration": inputs.duration,
-            "refinement": inputs.refinement,
-            "creativity": inputs.creativity,
-            "negative_prompt": inputs.negative_prompt,
-        }
-
-        # Add seed if provided
-        if inputs.seed is not None:
-            arguments["seed"] = inputs.seed
-
-        # Submit async job
-        handler = await fal_client.submit_async(
-            "beatoven/sound-effect-generation",
-            arguments=arguments,
-        )
-
-        # Store external job ID
-        await context.set_external_job_id(handler.request_id)
-
-        # Stream progress updates
-        from .....progress.models import ProgressUpdate
-
-        event_count = 0
-        async for event in handler.iter_events(with_logs=True):
-            event_count += 1
-            # Sample every 3rd event to avoid spam
-            if event_count % 3 == 0:
-                # Extract logs if available
-                logs = getattr(event, "logs", None)
-                if logs:
-                    # Join log entries into a single message
-                    if isinstance(logs, list):
-                        message = " | ".join(str(log) for log in logs if log)
-                    else:
-                        message = str(logs)
-
-                    if message:
-                        await context.publish_progress(
-                            ProgressUpdate(
-                                job_id=handler.request_id,
-                                status="processing",
-                                progress=50.0,
-                                phase="processing",
-                                message=message,
-                            )
-                        )
-
-        # Get final result
-        result = await handler.get()
-
-        # Extract audio from result
-        # fal.ai returns: {"audio": {"url": "...", "content_type": "...", ...}}
-        audio_data = result.get("audio")
-        if not audio_data:
-            raise ValueError("No audio returned from fal.ai API")
-
-        audio_url = audio_data.get("url")
-        if not audio_url:
-            raise ValueError("Audio missing URL in fal.ai response")
-
-        # Store audio result (WAV format)
-        artifact = await context.store_audio_result(
-            storage_url=audio_url,
-            format="wav",
-            output_index=0,
-        )
-
-        return GeneratorResult(outputs=[artifact])
-
-    async def estimate_cost(self, inputs: BeatovenSoundEffectGenerationInput) -> float:
-        """Estimate cost for this generation in USD.
-
-        Estimated at approximately $0.05 per sound effect generation.
-        Actual cost may vary based on duration and refinement settings.
-        """
-        return 0.05

package/templates/api/src/boards/generators/implementations/fal/audio/chatterbox_text_to_speech.py

@@ -1,176 +0,0 @@
-"""
-fal.ai Chatterbox Text-to-Speech generator.
-
-Generate expressive speech from text using Resemble AI's Chatterbox model.
-Supports emotive tags for natural expressions like laughing, sighing, and more.
-
-Based on Fal AI's fal-ai/chatterbox/text-to-speech model.
-See: https://fal.ai/models/fal-ai/chatterbox/text-to-speech
-"""
-
-import os
-
-from pydantic import BaseModel, Field
-
-from ....base import BaseGenerator, GeneratorExecutionContext, GeneratorResult
-
-
-class ChatterboxTextToSpeechInput(BaseModel):
-    """Input schema for Chatterbox text-to-speech generation.
-
-    Supports emotive tags: <laugh>, <chuckle>, <sigh>, <cough>,
-    <sniffle>, <groan>, <yawn>, <gasp>
-    """
-
-    text: str = Field(
-        description=(
-            "The text to be converted to speech. You can add emotive tags like "
-            "<laugh>, <chuckle>, <sigh>, <cough>, <sniffle>, <groan>, <yawn>, <gasp>"
-        ),
-        min_length=1,
-    )
-    audio_url: str | None = Field(
-        default=None,
-        description=(
-            "Reference audio file URL for voice style matching. "
-            "If not provided, uses a default voice sample."
-        ),
-    )
-    exaggeration: float = Field(
-        default=0.25,
-        ge=0.0,
-        le=1.0,
-        description="Speech exaggeration intensity factor (0.0 to 1.0)",
-    )
-    temperature: float = Field(
-        default=0.7,
-        ge=0.05,
-        le=2.0,
-        description="Creativity level for generation (0.05 to 2.0)",
-    )
-    cfg: float = Field(
-        default=0.5,
-        ge=0.1,
-        le=1.0,
-        description="Configuration parameter for generation (0.1 to 1.0)",
-    )
-    seed: int | None = Field(
-        default=None,
-        description="Random seed for reproducible audio generation",
-    )
-
-
-class FalChatterboxTextToSpeechGenerator(BaseGenerator):
-    """Chatterbox text-to-speech generator using fal.ai.
-
-    Leverages Resemble AI's Chatterbox model to generate expressive speech
-    with support for emotive tags and voice cloning via reference audio.
-    """
-
-    name = "fal-chatterbox-text-to-speech"
-    artifact_type = "audio"
-    description = (
-        "Fal: Chatterbox TTS - Expressive text-to-speech with emotive tags and voice cloning"
-    )
-
-    def get_input_schema(self) -> type[ChatterboxTextToSpeechInput]:
-        return ChatterboxTextToSpeechInput
-
-    async def generate(
-        self, inputs: ChatterboxTextToSpeechInput, context: GeneratorExecutionContext
-    ) -> GeneratorResult:
-        """Generate audio using fal.ai Chatterbox text-to-speech model."""
-        # Check for API key (fal-client uses FAL_KEY environment variable)
-        if not os.getenv("FAL_KEY"):
-            raise ValueError("API configuration invalid. Missing FAL_KEY environment variable")
-
-        # Import fal_client
-        try:
-            import fal_client
-        except ImportError as e:
-            raise ImportError(
-                "fal.ai SDK is required for FalChatterboxTextToSpeechGenerator. "
-                "Install with: pip install weirdfingers-boards[generators-fal]"
-            ) from e
-
-        # Prepare arguments for fal.ai API
-        arguments: dict = {
-            "text": inputs.text,
-            "exaggeration": inputs.exaggeration,
-            "temperature": inputs.temperature,
-            "cfg": inputs.cfg,
-        }
-
-        # Add optional parameters if provided
-        if inputs.audio_url is not None:
-            arguments["audio_url"] = inputs.audio_url
-        if inputs.seed is not None:
-            arguments["seed"] = inputs.seed
-
-        # Submit async job and get handler
-        handler = await fal_client.submit_async(
-            "fal-ai/chatterbox/text-to-speech",
-            arguments=arguments,
-        )
-
-        # Store the external job ID for tracking
-        await context.set_external_job_id(handler.request_id)
-
-        # Stream progress updates (sample every 3rd event to avoid spam)
-        from .....progress.models import ProgressUpdate
-
-        event_count = 0
-        async for event in handler.iter_events(with_logs=True):
-            event_count += 1
-
-            # Process every 3rd event to provide feedback without overwhelming
-            if event_count % 3 == 0:
-                # Extract logs if available
-                logs = getattr(event, "logs", None)
-                if logs:
-                    # Join log entries into a single message
-                    if isinstance(logs, list):
-                        message = " | ".join(str(log) for log in logs if log)
-                    else:
-                        message = str(logs)
-
-                    if message:
-                        await context.publish_progress(
-                            ProgressUpdate(
-                                job_id=handler.request_id,
-                                status="processing",
-                                progress=50.0,  # Approximate mid-point progress
-                                phase="processing",
-                                message=message,
-                            )
-                        )
-
-        # Get final result
-        result = await handler.get()
-
-        # Extract audio URL from result
-        # fal.ai returns: {"audio": {"url": "..."}}
-        audio_data = result.get("audio")
-        if audio_data is None:
-            raise ValueError("No audio data returned from fal.ai API")
-
-        audio_url = audio_data.get("url")
-        if not audio_url:
-            raise ValueError("Audio URL missing in fal.ai response")
-
-        # Store audio result
-        artifact = await context.store_audio_result(
-            storage_url=audio_url,
-            format="mp3",  # Chatterbox returns MP3 format
-            output_index=0,
-        )
-
-        return GeneratorResult(outputs=[artifact])
-
-    async def estimate_cost(self, inputs: ChatterboxTextToSpeechInput) -> float:
-        """Estimate cost for Chatterbox text-to-speech generation.
-
-        Chatterbox pricing is approximately $0.03 per generation.
-        """
-        # Fixed cost per generation
-        return 0.03