solana-agent 22.0.1__tar.gz → 22.0.2__tar.gz

{solana_agent-22.0.1 → solana_agent-22.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: solana-agent
-Version: 22.0.1
+Version: 22.0.2
 Summary: Agentic IQ
 License: MIT
 Keywords: ai,openai,ai agents,agi
@@ -249,6 +249,15 @@ async for response in solana_agent.process("user123", "Write me a poem.", intern
     print(response, end="")
 ```
 
+### Customize Audio Voice
+
+This is an audio to audio example using the `audio_instructions` parameter.
+
+```python
+async for response in solana_agent.process("user123", audio_content, output_format="audio", audio_voice="nova", audio_input_format="webm", audio_output_format="aac", audio_instructions="You speak with an American southern accent"):
+    print(response, end="")
+```
+
 ## Tools
 
 Tools can be used from plugins like Solana Agent Kit (sakit) or via custom inline tools. Tools available via plugins integrate automatically with Solana Agent.

{solana_agent-22.0.1 → solana_agent-22.0.2}/README.md

@@ -225,6 +225,15 @@ async for response in solana_agent.process("user123", "Write me a poem.", intern
     print(response, end="")
 ```
 
+### Customize Audio Voice
+
+This is an audio to audio example using the `audio_instructions` parameter.
+
+```python
+async for response in solana_agent.process("user123", audio_content, output_format="audio", audio_voice="nova", audio_input_format="webm", audio_output_format="aac", audio_instructions="You speak with an American southern accent"):
+    print(response, end="")
+```
+
 ## Tools
 
 Tools can be used from plugins like Solana Agent Kit (sakit) or via custom inline tools. Tools available via plugins integrate automatically with Solana Agent.

{solana_agent-22.0.1 → solana_agent-22.0.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "solana-agent"
-version = "22.0.1"
+version = "22.0.2"
 description = "Agentic IQ"
 authors = ["Bevan Hunt <bevan@bevanhunt.com>"]
 license = "MIT"

{solana_agent-22.0.1 → solana_agent-22.0.2}/solana_agent/adapters/llm_adapter.py

@@ -22,12 +22,12 @@ class OpenAIAdapter(LLMProvider):
         self.text_model = "gpt-4o-mini"
         self.internet_search_model = "gpt-4o-mini-search-preview"
         self.transcription_model = "gpt-4o-mini-transcribe"
-        self.tts_model = "tts-1"
+        self.tts_model = "gpt-4o-mini-tts"
 
     async def tts(
         self,
         text: str,
-        instructions: str = "",
+        instructions: str = "You speak in a friendly and helpful manner.",
         voice: Literal["alloy", "ash", "ballad", "coral", "echo",
                        "fable", "onyx", "nova", "sage", "shimmer"] = "nova",
         response_format: Literal['mp3', 'opus',
@@ -45,16 +45,16 @@ class OpenAIAdapter(LLMProvider):
             Audio bytes as they become available
         """
         try:
-            stream = self.client.audio.speech.create(
+            with self.client.audio.speech.with_streaming_response.create(
                 model=self.tts_model,
                 voice=voice,
+                instructions=instructions,
                 input=text,
                 response_format=response_format
-            )
-
-            # Stream the bytes in chunks
-            for chunk in stream.iter_bytes(chunk_size=1024 * 16):  # 16KB chunks
-                yield chunk
+            ) as stream:
+                # Stream the bytes in 16KB chunks
+                for chunk in stream.iter_bytes(chunk_size=1024 * 16):
+                    yield chunk
 
         except Exception as e:
             print(f"Error in text_to_speech: {str(e)}")
@@ -66,7 +66,7 @@ class OpenAIAdapter(LLMProvider):
             print(f"Error in text_to_speech: {str(e)}")
             import traceback
             print(traceback.format_exc())
-            yield f"I apologize, but I encountered an error converting text to speech: {str(e)}"
+            yield b""  # Return empty bytes on error
 
     async def transcribe_audio(
         self,
@@ -85,16 +85,14 @@ class OpenAIAdapter(LLMProvider):
             Transcript text chunks as they become available
         """
         try:
-            stream = self.client.audio.transcriptions.create(
+            with self.client.audio.transcriptions.with_streaming_response.create(
                 model=self.transcription_model,
                 file=(f"file.{input_format}", audio_bytes),
                 response_format="text",
-                stream=True
-            )
-
-            for event in stream:
-                if hasattr(event, 'text') and event.text:
-                    yield event.text
+            ) as stream:
+                # Stream the text in 16KB chunks
+                for chunk in stream.iter_text(chunk_size=1024 * 16):
+                    yield chunk
 
         except Exception as e:
             print(f"Error in transcribe_audio: {str(e)}")

{solana_agent-22.0.1 → solana_agent-22.0.2}/solana_agent/client/solana_agent.py

@@ -49,7 +49,7 @@ class SolanaAgent(SolanaAgentInterface):
         output_format: Literal["text", "audio"] = "text",
         audio_voice: Literal["alloy", "ash", "ballad", "coral", "echo",
                              "fable", "onyx", "nova", "sage", "shimmer"] = "nova",
-        audio_instructions: Optional[str] = None,
+        audio_instructions: str = "You speak in a friendly and helpful manner.",
         audio_output_format: Literal['mp3', 'opus',
                                      'aac', 'flac', 'wav', 'pcm'] = "aac",
         audio_input_format: Literal[
@@ -66,7 +66,7 @@ class SolanaAgent(SolanaAgentInterface):
             prompt: Optional prompt for the agent
             output_format: Response format ("text" or "audio")
             audio_voice: Voice to use for audio output
-            audio_instructions: Not used currently
+            audio_instructions: Audio voice instructions
             audio_output_format: Audio output format
             audio_input_format: Audio input format
             router: Optional routing service for processing

{solana_agent-22.0.1 → solana_agent-22.0.2}/solana_agent/interfaces/client/client.py

@@ -17,7 +17,7 @@ class SolanaAgent(ABC):
         output_format: Literal["text", "audio"] = "text",
         audio_voice: Literal["alloy", "ash", "ballad", "coral", "echo",
                              "fable", "onyx", "nova", "sage", "shimmer"] = "nova",
-        audio_instructions: Optional[str] = None,
+        audio_instructions: str = "You speak in a friendly and helpful manner.",
         audio_output_format: Literal['mp3', 'opus',
                                      'aac', 'flac', 'wav', 'pcm'] = "aac",
         audio_input_format: Literal[

{solana_agent-22.0.1 → solana_agent-22.0.2}/solana_agent/interfaces/providers/llm.py

@@ -31,7 +31,7 @@ class LLMProvider(ABC):
     async def tts(
         self,
         text: str,
-        instructions: str = "",
+        instructions: str = "You speak in a friendly and helpful manner.",
         voice: Literal["alloy", "ash", "ballad", "coral", "echo",
                        "fable", "onyx", "nova", "sage", "shimmer"] = "nova",
         response_format: Literal['mp3', 'opus',

{solana_agent-22.0.1 → solana_agent-22.0.2}/solana_agent/interfaces/services/agent.py

@@ -27,7 +27,7 @@ class AgentService(ABC):
         output_format: Literal["text", "audio"] = "text",
         audio_voice: Literal["alloy", "ash", "ballad", "coral", "echo",
                              "fable", "onyx", "nova", "sage", "shimmer"] = "nova",
-        audio_instructions: Optional[str] = None,
+        audio_instructions: str = "You speak in a friendly and helpful manner.",
         audio_output_format: Literal['mp3', 'opus',
                                      'aac', 'flac', 'wav', 'pcm'] = "aac",
         audio_input_format: Literal[

{solana_agent-22.0.1 → solana_agent-22.0.2}/solana_agent/interfaces/services/query.py

@@ -13,7 +13,7 @@ class QueryService(ABC):
         output_format: Literal["text", "audio"] = "text",
         audio_voice: Literal["alloy", "ash", "ballad", "coral", "echo",
                              "fable", "onyx", "nova", "sage", "shimmer"] = "nova",
-        audio_instructions: Optional[str] = None,
+        audio_instructions: str = "You speak in a friendly and helpful manner.",
         audio_output_format: Literal['mp3', 'opus',
                                      'aac', 'flac', 'wav', 'pcm'] = "aac",
         audio_input_format: Literal[

{solana_agent-22.0.1 → solana_agent-22.0.2}/solana_agent/services/agent.py

@@ -169,7 +169,7 @@ class AgentService(AgentServiceInterface):
         output_format: Literal["text", "audio"] = "text",
         audio_voice: Literal["alloy", "ash", "ballad", "coral", "echo",
                              "fable", "onyx", "nova", "sage", "shimmer"] = "nova",
-        audio_instructions: Optional[str] = None,
+        audio_instructions: str = "You speak in a friendly and helpful manner.",
         audio_output_format: Literal['mp3', 'opus',
                                      'aac', 'flac', 'wav', 'pcm'] = "aac",
         audio_input_format: Literal[

{solana_agent-22.0.1 → solana_agent-22.0.2}/solana_agent/services/query.py

@@ -41,7 +41,7 @@ class QueryService(QueryServiceInterface):
         output_format: Literal["text", "audio"] = "text",
         audio_voice: Literal["alloy", "ash", "ballad", "coral", "echo",
                              "fable", "onyx", "nova", "sage", "shimmer"] = "nova",
-        audio_instructions: Optional[str] = None,
+        audio_instructions: str = "You speak in a friendly and helpful manner.",
         audio_output_format: Literal['mp3', 'opus',
                                      'aac', 'flac', 'wav', 'pcm'] = "aac",
         audio_input_format: Literal[
@@ -58,7 +58,7 @@ class QueryService(QueryServiceInterface):
             query: Text query or audio bytes
             output_format: Response format ("text" or "audio")
             audio_voice: Voice for TTS (text-to-speech)
-            audio_instructions: Optional instructions for TTS
+            audio_instructions: Audio voice instructions
             audio_output_format: Audio output format
             audio_input_format: Audio input format
             prompt: Optional prompt for the agent
@@ -84,7 +84,8 @@ class QueryService(QueryServiceInterface):
                     async for chunk in self.agent_service.llm_provider.tts(
                         text=response,
                         voice=audio_voice,
-                        response_format=audio_output_format
+                        response_format=audio_output_format,
+                        instructions=audio_instructions,
                     ):
                         yield chunk
                 else: