audiopod 1.0.0__py3-none-any.whl → 1.1.0__py3-none-any.whl

audiopod/__init__.py

@@ -47,7 +47,7 @@ from .models import (
     TranslationResult
 )
 
-__version__ = "1.0.0"
+__version__ = "1.1.0"
 __author__ = "AudioPod AI"
 __email__ = "support@audiopod.ai"
 __license__ = "MIT"

audiopod/client.py

@@ -23,7 +23,8 @@ from .services import (
     SpeakerService,
     DenoiserService,
     KaraokeService,
-    CreditService
+    CreditService,
+    StemExtractionService
 )
 
 logger = logging.getLogger(__name__)
@@ -139,6 +140,7 @@ class Client(BaseClient):
         self.denoiser = DenoiserService(self)
         self.karaoke = KaraokeService(self)
         self.credits = CreditService(self)
+        self.stem_extraction = StemExtractionService(self)
         
     def request(
         self,
@@ -227,6 +229,7 @@ class AsyncClient(BaseClient):
         self.denoiser = DenoiserService(self, async_mode=True)
         self.karaoke = KaraokeService(self, async_mode=True)
         self.credits = CreditService(self, async_mode=True)
+        self.stem_extraction = StemExtractionService(self, async_mode=True)
         
     @property
     def session(self) -> aiohttp.ClientSession:

audiopod/py.typed

@@ -0,0 +1,2 @@
+# Marker file for PEP 561
+# This package supports type checking

audiopod/services/__init__.py

@@ -11,6 +11,7 @@ from .speaker import SpeakerService
 from .denoiser import DenoiserService
 from .karaoke import KaraokeService
 from .credits import CreditService
+from .stem_extraction import StemExtractionService
 
 __all__ = [
     "VoiceService",
@@ -20,5 +21,6 @@ __all__ = [
     "SpeakerService",
     "DenoiserService",
     "KaraokeService",
-    "CreditService"
+    "CreditService",
+    "StemExtractionService"
 ]

audiopod/services/music.py

@@ -51,15 +51,15 @@ class MusicService(BaseService):
         if seed is not None and (seed < 0 or seed > 2**32 - 1):
             raise ValidationError("Seed must be between 0 and 2^32 - 1")
             
-        # Prepare request data
+        # Prepare request data - FIXED: Use correct parameter names matching API schema
         data = {
             "prompt": prompt,
-            "duration": duration,
+            "audio_duration": duration,  # FIXED: API expects "audio_duration" not "duration"
             "guidance_scale": guidance_scale,
-            "num_inference_steps": num_inference_steps
+            "infer_step": num_inference_steps  # FIXED: API expects "infer_step" not "num_inference_steps"
         }
         if seed is not None:
-            data["seed"] = seed
+            data["manual_seeds"] = [seed]  # FIXED: API expects "manual_seeds" list not "seed"
         if display_name:
             data["display_name"] = display_name.strip()
             
@@ -68,7 +68,9 @@ class MusicService(BaseService):
             return self._async_generate_music(data, wait_for_completion, timeout)
         else:
             response = self.client.request("POST", "/api/v1/music/text2music", data=data)
-            job = Job.from_dict(response)
+            # FIXED: Handle response format correctly - API returns {"job": {...}, "message": "..."}
+            job_data = response.get("job", response)
+            job = Job.from_dict(job_data)
             
             if wait_for_completion:
                 completed_job = self._wait_for_completion(job.id, timeout)
@@ -84,7 +86,9 @@ class MusicService(BaseService):
     ) -> Union[Job, MusicGenerationResult]:
         """Async version of generate_music"""
         response = await self.client.request("POST", "/api/v1/music/text2music", data=data)
-        job = Job.from_dict(response)
+        # FIXED: Handle response format correctly
+        job_data = response.get("job", response)
+        job = Job.from_dict(job_data)
         
         if wait_for_completion:
             completed_job = await self._async_wait_for_completion(job.id, timeout)
@@ -122,11 +126,14 @@ class MusicService(BaseService):
         if style not in ["modern", "classic", "trap"]:
             raise ValidationError("Style must be 'modern', 'classic', or 'trap'")
             
-        # Prepare request data
+        # Prepare request data - FIXED: Match API schema for text2rap
         data = {
+            "prompt": f"rap music, {style} style",  # FIXED: API expects "prompt" field
             "lyrics": lyrics,
-            "style": style,
-            "tempo": tempo
+            "audio_duration": 120.0,  # Default duration
+            "guidance_scale": 7.5,
+            "infer_step": 50,
+            "lora_name_or_path": "ACE-Step/ACE-Step-v1-chinese-rap-LoRA"  # Rap-specific LoRA
         }
         if display_name:
             data["display_name"] = display_name.strip()
@@ -136,7 +143,9 @@ class MusicService(BaseService):
             return self._async_generate_rap(data, wait_for_completion, timeout)
         else:
             response = self.client.request("POST", "/api/v1/music/text2rap", data=data)
-            job = Job.from_dict(response)
+            # FIXED: Handle response format correctly
+            job_data = response.get("job", response)
+            job = Job.from_dict(job_data)
             
             if wait_for_completion:
                 completed_job = self._wait_for_completion(job.id, timeout)
@@ -152,7 +161,9 @@ class MusicService(BaseService):
     ) -> Union[Job, MusicGenerationResult]:
         """Async version of generate_rap"""
         response = await self.client.request("POST", "/api/v1/music/text2rap", data=data)
-        job = Job.from_dict(response)
+        # FIXED: Handle response format correctly
+        job_data = response.get("job", response)
+        job = Job.from_dict(job_data)
         
         if wait_for_completion:
             completed_job = await self._async_wait_for_completion(job.id, timeout)
@@ -194,10 +205,12 @@ class MusicService(BaseService):
         if tempo is not None and not 60 <= tempo <= 200:
             raise ValidationError("Tempo must be between 60 and 200 BPM")
             
-        # Prepare request data
+        # Prepare request data - FIXED: Match API schema for prompt2instrumental
         data = {
             "prompt": prompt,
-            "duration": duration
+            "audio_duration": duration,  # FIXED: API expects "audio_duration"
+            "guidance_scale": 7.5,
+            "infer_step": 50
         }
         if instruments:
             data["instruments"] = instruments
@@ -213,7 +226,9 @@ class MusicService(BaseService):
             return self._async_generate_instrumental(data, wait_for_completion, timeout)
         else:
             response = self.client.request("POST", "/api/v1/music/prompt2instrumental", data=data)
-            job = Job.from_dict(response)
+            # FIXED: Handle response format correctly
+            job_data = response.get("job", response)
+            job = Job.from_dict(job_data)
             
             if wait_for_completion:
                 completed_job = self._wait_for_completion(job.id, timeout)
@@ -229,7 +244,80 @@ class MusicService(BaseService):
     ) -> Union[Job, MusicGenerationResult]:
         """Async version of generate_instrumental"""
         response = await self.client.request("POST", "/api/v1/music/prompt2instrumental", data=data)
-        job = Job.from_dict(response)
+        # FIXED: Handle response format correctly
+        job_data = response.get("job", response)
+        job = Job.from_dict(job_data)
+        
+        if wait_for_completion:
+            completed_job = await self._async_wait_for_completion(job.id, timeout)
+            return MusicGenerationResult.from_dict(completed_job.result or completed_job.__dict__)
+            
+        return job
+    
+    def generate_vocals(
+        self,
+        lyrics: str,
+        prompt: str = "vocals",
+        duration: float = 120.0,
+        display_name: Optional[str] = None,
+        wait_for_completion: bool = False,
+        timeout: int = 600
+    ) -> Union[Job, MusicGenerationResult]:
+        """
+        Generate vocals from lyrics - NEW METHOD matching API lyric2vocals endpoint
+        
+        Args:
+            lyrics: Song lyrics
+            prompt: Vocal style description
+            duration: Duration in seconds
+            display_name: Custom name for the track
+            wait_for_completion: Whether to wait for completion
+            timeout: Maximum time to wait
+            
+        Returns:
+            Job object or generation result
+        """
+        # Validate inputs
+        lyrics = self._validate_text_input(lyrics, max_length=10000)
+        prompt = self._validate_text_input(prompt, max_length=2000)
+        if not 10.0 <= duration <= 600.0:
+            raise ValidationError("Duration must be between 10 and 600 seconds")
+            
+        # Prepare request data - Match API schema for lyric2vocals
+        data = {
+            "prompt": prompt,
+            "lyrics": lyrics,
+            "audio_duration": duration,
+            "guidance_scale": 7.5,
+            "infer_step": 50
+        }
+        if display_name:
+            data["display_name"] = display_name.strip()
+            
+        # Make request
+        if self.async_mode:
+            return self._async_generate_vocals(data, wait_for_completion, timeout)
+        else:
+            response = self.client.request("POST", "/api/v1/music/lyric2vocals", data=data)
+            job_data = response.get("job", response)
+            job = Job.from_dict(job_data)
+            
+            if wait_for_completion:
+                completed_job = self._wait_for_completion(job.id, timeout)
+                return MusicGenerationResult.from_dict(completed_job.result or completed_job.__dict__)
+                
+            return job
+    
+    async def _async_generate_vocals(
+        self,
+        data: Dict[str, Any],
+        wait_for_completion: bool,
+        timeout: int
+    ) -> Union[Job, MusicGenerationResult]:
+        """Async version of generate_vocals"""
+        response = await self.client.request("POST", "/api/v1/music/lyric2vocals", data=data)
+        job_data = response.get("job", response)
+        job = Job.from_dict(job_data)
         
         if wait_for_completion:
             completed_job = await self._async_wait_for_completion(job.id, timeout)
@@ -322,7 +410,7 @@ class MusicService(BaseService):
         """
         params = {
             "limit": limit,
-            "skip": offset
+            "skip": offset  # FIXED: API uses "skip" parameter for offset
         }
         if status:
             params["status"] = status

audiopod/services/stem_extraction.py

@@ -0,0 +1,180 @@
+"""
+Stem Extraction Service - Audio stem separation operations
+"""
+
+from typing import List, Optional, Dict, Any, Union
+from .base import BaseService
+from ..models import Job
+from ..exceptions import ValidationError
+
+
+class StemExtractionService(BaseService):
+    """Service for audio stem extraction operations"""
+    
+    def extract_stems(
+        self,
+        audio_file: Optional[str] = None,
+        url: Optional[str] = None,
+        stem_types: List[str] = None,
+        model_name: str = "htdemucs",
+        two_stems_mode: Optional[str] = None,
+        wait_for_completion: bool = False,
+        timeout: int = 900
+    ) -> Job:
+        """
+        Extract stems from audio file
+        
+        Args:
+            audio_file: Path to audio file to process
+            url: URL of audio file to process (alternative to audio_file)
+            stem_types: List of stems to extract (e.g., ['vocals', 'drums', 'bass', 'other'])
+            model_name: Model to use for separation ('htdemucs' or 'htdemucs_6s')
+            two_stems_mode: Two-stem mode for vocals/instrumental separation
+            wait_for_completion: Whether to wait for completion
+            timeout: Maximum time to wait
+            
+        Returns:
+            Job object with stem extraction details
+        """
+        if not audio_file and not url:
+            raise ValidationError("Either audio_file or url must be provided")
+        
+        if audio_file and url:
+            raise ValidationError("Provide either audio_file or url, not both")
+        
+        # Set default stem types based on model
+        if stem_types is None:
+            if model_name == "htdemucs_6s":
+                stem_types = ["vocals", "drums", "bass", "other", "piano", "guitar"]
+            else:
+                stem_types = ["vocals", "drums", "bass", "other"]
+        
+        # Validate model name
+        if model_name not in ["htdemucs", "htdemucs_6s"]:
+            raise ValidationError("Model name must be 'htdemucs' or 'htdemucs_6s'")
+        
+        # Prepare request
+        files = {}
+        data = {
+            "stem_types": str(stem_types),  # API expects string representation
+            "model_name": model_name
+        }
+        
+        if audio_file:
+            files = self._prepare_file_upload(audio_file, "file")
+        
+        if url:
+            data["url"] = url
+        
+        if two_stems_mode:
+            data["two_stems_mode"] = two_stems_mode
+        
+        if self.async_mode:
+            return self._async_extract_stems(files, data, wait_for_completion, timeout)
+        else:
+            response = self.client.request(
+                "POST", 
+                "/api/v1/stem-extraction/extract",
+                data=data,
+                files=files if files else None
+            )
+            
+            job = Job.from_dict(response)
+            
+            if wait_for_completion:
+                return self._wait_for_completion(job.id, timeout)
+            
+            return job
+    
+    async def _async_extract_stems(
+        self,
+        files: Dict[str, Any],
+        data: Dict[str, Any],
+        wait_for_completion: bool,
+        timeout: int
+    ) -> Job:
+        """Async version of extract_stems"""
+        response = await self.client.request(
+            "POST",
+            "/api/v1/stem-extraction/extract",
+            data=data,
+            files=files if files else None
+        )
+        
+        job = Job.from_dict(response)
+        
+        if wait_for_completion:
+            return await self._async_wait_for_completion(job.id, timeout)
+        
+        return job
+    
+    def get_stem_job(self, job_id: int) -> Job:
+        """
+        Get stem extraction job status
+        
+        Args:
+            job_id: ID of the stem extraction job
+            
+        Returns:
+            Job object with current status
+        """
+        if self.async_mode:
+            return self._async_get_stem_job(job_id)
+        else:
+            response = self.client.request("GET", f"/api/v1/stem-extraction/status/{job_id}")
+            return Job.from_dict(response)
+    
+    async def _async_get_stem_job(self, job_id: int) -> Job:
+        """Async version of get_stem_job"""
+        response = await self.client.request("GET", f"/api/v1/stem-extraction/status/{job_id}")
+        return Job.from_dict(response)
+    
+    def list_stem_jobs(
+        self,
+        skip: int = 0,
+        limit: int = 50
+    ) -> List[Job]:
+        """
+        List stem extraction jobs
+        
+        Args:
+            skip: Number of jobs to skip
+            limit: Maximum number of jobs to return
+            
+        Returns:
+            List of stem extraction jobs
+        """
+        params = {
+            "skip": skip,
+            "limit": limit
+        }
+        
+        if self.async_mode:
+            return self._async_list_stem_jobs(params)
+        else:
+            response = self.client.request("GET", "/api/v1/stem-extraction/jobs", params=params)
+            return [Job.from_dict(job_data) for job_data in response]
+    
+    async def _async_list_stem_jobs(self, params: Dict[str, Any]) -> List[Job]:
+        """Async version of list_stem_jobs"""
+        response = await self.client.request("GET", "/api/v1/stem-extraction/jobs", params=params)
+        return [Job.from_dict(job_data) for job_data in response]
+    
+    def delete_stem_job(self, job_id: int) -> Dict[str, str]:
+        """
+        Delete a stem extraction job
+        
+        Args:
+            job_id: ID of the job to delete
+            
+        Returns:
+            Deletion confirmation
+        """
+        if self.async_mode:
+            return self._async_delete_stem_job(job_id)
+        else:
+            return self.client.request("DELETE", f"/api/v1/stem-extraction/jobs/{job_id}")
+    
+    async def _async_delete_stem_job(self, job_id: int) -> Dict[str, str]:
+        """Async version of delete_stem_job"""
+        return await self.client.request("DELETE", f"/api/v1/stem-extraction/jobs/{job_id}")

{audiopod-1.0.0.dist-info → audiopod-1.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: audiopod
-Version: 1.0.0
+Version: 1.1.0
 Summary: Professional Audio Processing API Client for Python
 Home-page: https://github.com/audiopod-ai/audiopod-python
 Author: AudioPod AI
@@ -25,6 +25,7 @@ Classifier: Topic :: Multimedia :: Sound/Audio :: Conversion
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
+License-File: LICENSE
 Requires-Dist: requests>=2.28.0
 Requires-Dist: aiohttp>=3.8.0
 Requires-Dist: pydantic>=1.10.0
@@ -46,6 +47,7 @@ Requires-Dist: sphinx-rtd-theme>=1.2.0; extra == "docs"
 Requires-Dist: sphinx-autodoc-typehints>=1.19.0; extra == "docs"
 Dynamic: author
 Dynamic: home-page
+Dynamic: license-file
 Dynamic: requires-python
 
 # AudioPod Python SDK
@@ -380,11 +382,10 @@ audiopod transcription transcribe audio.mp3 --language en
 
 ## Support
 
-- 📖 [Documentation](https://docs.audiopod.ai)
-- 🎯 [API Reference](https://api.audiopod.ai/docs) 
+- 📖 [API Reference](https://docs.audiopod.ai)
 - 💬 [Discord Community](https://discord.gg/audiopod)
 - 📧 [Email Support](mailto:support@audiopod.ai)
-- 🐛 [Bug Reports](https://github.com/audiopod-ai/audiopod-python/issues)
+- 🐛 [Bug Reports](https://github.com/AudiopodAI/audiopod)
 
 ## License
 

{audiopod-1.0.0.dist-info → audiopod-1.1.0.dist-info}/RECORD

@@ -1,21 +1,24 @@
-audiopod/__init__.py,sha256=GyQ7PUWGF3t4Ljuk_DD6O9MvG_A96T5bedXc3jJQCD4,1790
+audiopod/__init__.py,sha256=U12jbLmXps3-NP3yXcucGMQbr8b6VCoWAXZSitK1pp4,1790
 audiopod/cli.py,sha256=ZYzAQ3UpoYuOEWivMwMneJUf2z8DGGYTx1Nb6yRfdVY,9339
-audiopod/client.py,sha256=AF5goB5CG5lJZ3XyGojRskvUNrNzn9A34BAx9Z1sEOE,11580
+audiopod/client.py,sha256=67oPSInSNssJpTR00ZuYSdk9lbx5KiRnDQw8UYKNVsA,11742
 audiopod/config.py,sha256=fuGtbuES4tXdHwqQqoZa5izCH6nVfFRP06D8eK1Cg10,1683
 audiopod/exceptions.py,sha256=c3Ym2tWyRE1kemVkXDaXFcfP3h6AokhKcUcCBImwGes,2386
 audiopod/models.py,sha256=gAfQkufA_hZdYBkniFJ_EXETy9ts-wr-soUEbT7ZKFM,7827
-audiopod/services/__init__.py,sha256=rt_9CHqmEJgHyVFdF2WwTE403CXpDGBCYzfCxJZZjgE,573
+audiopod/py.typed,sha256=ixa8YukDZ3kLo0WsFJRGohLMyHzbMur1ALmmASML2cs,64
+audiopod/services/__init__.py,sha256=9Ycl9VVscwwY42joBCSL67v8DrITW2T2QyuaokbpehM,653
 audiopod/services/base.py,sha256=mNbziYy2KsWWZrdHFlTl9pKLvoQUW-ZkkJuVWfCVP74,6731
 audiopod/services/credits.py,sha256=CjE2W8kmYjM4B02BwfPvvB3kl0YdVimM2kR7lhg43h8,1796
 audiopod/services/denoiser.py,sha256=Oi_1rCKs_L5lCG_2QuKwHzLe8_mbEIzlzM2X8TJ7Rnc,1750
 audiopod/services/karaoke.py,sha256=M0Befh4Y2DNM_uWFTmCIrzKfjqkvygrzCt0f_Dubj2o,2012
-audiopod/services/music.py,sha256=m6cF_2cbB4X-BHvJH36oqD2NBF_dIWCAUB2HIpZgoxo,15948
+audiopod/services/music.py,sha256=hDPjTSj-gAeEWBVB7PRPQrptMHJyQTz8e9p-p7yaRPI,20032
 audiopod/services/speaker.py,sha256=OPSOwArfrGXVzRgciS13n1QsCJSK1PB-Mz6VgwxuHAA,1866
+audiopod/services/stem_extraction.py,sha256=3ibMFKFR25xKHpVs3WGMNriZ88sB5PriFNa_s2Bvon4,6026
 audiopod/services/transcription.py,sha256=HyH6WpGWZsggYxIvt2dhB6_5UHaigk3XwXsVgarWzcE,7565
 audiopod/services/translation.py,sha256=Gpxmom-ZSLMXBwSQlOL5PyqxQCwRYNT2IUp2ZD5QhYc,3177
 audiopod/services/voice.py,sha256=_IHv3zU3k184kfijxr1QRBenrIpmhhPOBS96DddZ8yw,13456
-audiopod-1.0.0.dist-info/METADATA,sha256=S7iD1nLEk-xXknM1K8sze0ucL2oVGtxcXpvtIFRGtTY,10956
-audiopod-1.0.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-audiopod-1.0.0.dist-info/entry_points.txt,sha256=uLcNDzXuOXnJAz9j91TDGayVjjZ7-ZiHBGDydqNUErU,47
-audiopod-1.0.0.dist-info/top_level.txt,sha256=M6yyOFFNpLdH4i1AMRqJZLRIgfpg1NvrQVmnPd8A6N8,9
-audiopod-1.0.0.dist-info/RECORD,,
+audiopod-1.1.0.dist-info/licenses/LICENSE,sha256=hqEjnOaGNbnLSBxbtbC7WQVREU2vQI8FmwecCiZlMfA,1068
+audiopod-1.1.0.dist-info/METADATA,sha256=ee2Zg4iwkglAgnk3xwNuYg11LFZbKJQeUcxgG8Z_Dw0,10931
+audiopod-1.1.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+audiopod-1.1.0.dist-info/entry_points.txt,sha256=uLcNDzXuOXnJAz9j91TDGayVjjZ7-ZiHBGDydqNUErU,47
+audiopod-1.1.0.dist-info/top_level.txt,sha256=M6yyOFFNpLdH4i1AMRqJZLRIgfpg1NvrQVmnPd8A6N8,9
+audiopod-1.1.0.dist-info/RECORD,,

audiopod-1.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 AudioPod AI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.