Re - feat(pipecat-sdk): add speech-to-speech model support (Gemini Live) (#683)pipecat-update

#### RE-RAISING Pipecat live speech PR

### Added native speech-to-speech model support

### Summary:
  - Speech-to-speech support - Auto-detect audio frames and inject memories to system prompt for native audio models (Gemini Live, etc.)
  - Fix memory bloating - Replace memories each turn using XML tags instead of accumulating
  - Add temporal context - Show recency on search results ([2d ago], [15 Jan])
  - New inject_mode param - auto (default), system, or user

### Docs update
  - Update the docs for native speech-2-speech models

1 files changed, 53 insertions, 13 deletions

diff --git a/apps/docs/integrations/pipecat.mdx b/apps/docs/integrations/pipecat.mdx
index c96f27e1..a5cae1e9 100644
--- a/apps/docs/integrations/pipecat.mdx
+++ b/apps/docs/integrations/pipecat.mdx
@@ -28,7 +28,8 @@ You can obtain an API key from [console.supermemory.ai](https://console.supermem
 Supermemory integration is provided through the `SupermemoryPipecatService` class in Pipecat:
 
 ```python
-from supermemory_pipecat import SupermemoryPipecatService, InputParams
+from supermemory_pipecat import SupermemoryPipecatService
+from supermemory_pipecat.service import InputParams
 
 memory = SupermemoryPipecatService(
     api_key=os.getenv("SUPERMEMORY_API_KEY"),
@@ -78,11 +79,11 @@ Retrieved memories are formatted and injected into the LLM context before genera
 
 ## Memory Modes
 
-| Mode | Static Profile | Dynamic Profile | Search Results | Use Case |
-|------|----------------|-----------------|----------------|----------|
-| `"profile"` | Yes | Yes | No | Personalization without search |
-| `"query"` | No | No | Yes | Finding relevant past context |
-| `"full"` | Yes | Yes | Yes | Complete memory (default) |
+| Mode        | Static Profile | Dynamic Profile | Search Results | Use Case                       |
+| ----------- | -------------- | --------------- | -------------- | ------------------------------ |
+| `"profile"` | Yes            | Yes             | No             | Personalization without search |
+| `"query"`   | No             | No              | Yes            | Finding relevant past context  |
+| `"full"`    | Yes            | Yes             | Yes            | Complete memory (default)      |
 
 ## Configuration Options
 
@@ -96,15 +97,41 @@ InputParams(
     search_limit=10,           # Max memories to retrieve (default: 10)
     search_threshold=0.1,      # Similarity threshold 0.0-1.0 (default: 0.1)
     system_prompt="Based on previous conversations:\n\n",
+    inject_mode="auto",        # "auto" | "system" | "user"
 )
 ```
 
-| Parameter | Type | Default | Description |
-|-----------|------|---------|-------------|
-| `search_limit` | int | 10 | Maximum number of memories to retrieve per query |
-| `search_threshold` | float | 0.1 | Minimum similarity threshold for memory retrieval |
-| `mode` | str | "full" | Memory retrieval mode: `"profile"`, `"query"`, or `"full"` |
-| `system_prompt` | str | "Based on previous conversations:\n\n" | Prefix text for memory context |
+| Parameter          | Type  | Default                                | Description                                                  |
+| ------------------ | ----- | -------------------------------------- | ------------------------------------------------------------ |
+| `search_limit`     | int   | 10                                     | Maximum number of memories to retrieve per query             |
+| `search_threshold` | float | 0.1                                    | Minimum similarity threshold for memory retrieval            |
+| `mode`             | str   | "full"                                 | Memory retrieval mode: `"profile"`, `"query"`, or `"full"`   |
+| `system_prompt`    | str   | "Based on previous conversations:\n\n" | Prefix text for memory context                               |
+| `inject_mode`      | str   | "auto"                                 | How memories are injected: `"auto"`, `"system"`, or `"user"` |
+
+## Injection Modes
+
+The `inject_mode` parameter controls how memories are added to the LLM context:
+
+| Mode       | Behavior                                                                                                                                                                |
+| ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `"auto"`   | **Auto-detects** based on frame types. If audio frames detected → injects to system prompt (speech-to-speech). If only text frames → injects as user message (STT/TTS). |
+| `"system"` | Always injects memories into the system prompt                                                                                                                          |
+| `"user"`   | Always injects memories as a user message                                                                                                                               |
+
+## Speech-to-Speech Models (Gemini Live, etc.)
+
+For speech-to-speech models like Gemini Live, the SDK **automatically detects** audio frames and injects memories into the system prompt. No configuration needed:
+
+```python
+from supermemory_pipecat import SupermemoryPipecatService
+
+# Auto-detection works out of the box
+memory = SupermemoryPipecatService(
+    api_key=os.getenv("SUPERMEMORY_API_KEY"),
+    user_id="unique_user_id",
+)
+```
 
 ## Example: Voice Agent with Memory
 
@@ -130,7 +157,8 @@ from pipecat.transports.websocket.fastapi import (
     FastAPIWebsocketTransport,
 )
 
-from supermemory_pipecat import SupermemoryPipecatService, InputParams
+from supermemory_pipecat import SupermemoryPipecatService
+from supermemory_pipecat.service import InputParams
 
 app = FastAPI()
 
@@ -201,3 +229,15 @@ if __name__ == "__main__":
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=8000)
 ```
+
+## Example: Gemini Live with Memory
+
+For a complete example using Gemini Live speech-to-speech with Supermemory, check out the reference implementation:
+
+<Card
+  title="Pipecat Memory Example"
+  icon="github"
+  href="https://github.com/supermemoryai/pipecat-memory"
+>
+  Full working example with Gemini Live, including frontend and backend code.
+</Card>