Merge pull request #83 from pipecat-ai/mb/docs-2025-01-08

AWS and Gemini updates
pipecat-ai · Jan 8, 2025 · 08e4e9e · 08e4e9e
2 parents 35611a7 + de24265
commit 08e4e9e
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 7 deletions.
diff --git a/server/services/s2s/gemini.mdx b/server/services/s2s/gemini.mdx
@@ -10,15 +10,11 @@ The `GeminiMultimodalLiveLLMService` enables natural, real-time conversations wi
     Stream audio and video in real-time with low latency response times
   </Card>
 
-{" "}
-
 <Card title="Speech Processing" icon="waveform-lines">
   Built-in speech-to-text and text-to-speech capabilities with multiple voice
   options
 </Card>
 
-{" "}
-
 <Card title="Voice Activity Detection" icon="microphone">
   Automatic detection of speech start/stop for natural conversations
 </Card>
@@ -127,6 +123,10 @@ llm = GeminiMultimodalLiveLLMService(
   Maximum number of tokens to generate
 </ParamField>
 
+<ParamField path="modalities" type="enum" optional default="AUDIO">
+  Response modalities to include (options: `AUDIO`, `TEXT`).
+</ParamField>
+
 <ParamField path="presence_penalty" type="float" optional default="None">
   Penalizes tokens based on their presence in the text. Range: 0.0 to 2.0
 </ParamField>

diff --git a/server/services/tts/aws.mdx b/server/services/tts/aws.mdx
@@ -25,15 +25,15 @@ You'll also need to set up your AWS credentials as environment variables:
 
 ### Constructor Parameters
 
-<ParamField path="api_key" type="str" required>
+<ParamField path="api_key" type="str">
   AWS secret access key
 </ParamField>
 
-<ParamField path="aws_access_key_id" type="str" required>
+<ParamField path="aws_access_key_id" type="str">
   AWS access key ID
 </ParamField>
 
-<ParamField path="region" type="str" required>
+<ParamField path="region" type="str">
   AWS region name
 </ParamField>