Merge pull request #2135 from pipecat-ai/aleix/pipecat-0.0.74

update CHANGELOG for 0.0.74

CHANGELOG.md

@@ -5,17 +5,19 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [0.0.74] - 2025-07-03
 
 ### Added
 
-- Added a new STT service, `SpeechmaticsSTTService`. This service provides 
+- Added a new STT service, `SpeechmaticsSTTService`. This service provides
   real-time speech-to-text transcription using the Speechmatics API. It supports
-  partial and final transcriptions, multiple languages, various audio formats, 
+  partial and final transcriptions, multiple languages, various audio formats,
   and speaker diarization.
 
 - Added `normalize` and `model_id` to `FishAudioTTSService`.
 
+- Added `http_options` argument to `GoogleLLMService`.
+
 - Added `run_llm` field to `LLMMessagesAppendFrame` and `LLMMessagesUpdateFrame`
   frames. If true, a context frame will be pushed triggering the LLM to respond.
 
@@ -57,9 +59,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   tools = ToolsSchema(standard_tools=[do_something])
   ```
 
-  - `user_id` is now populated in the `TranscriptionFrame` and
-    `InterimTranscriptionFrame` when using a transport that provides a
-    `user_id`, like `DailyTransport` or `LiveKitTransport`.
+- `user_id` is now populated in the `TranscriptionFrame` and
+  `InterimTranscriptionFrame` when using a transport that provides a `user_id`,
+  like `DailyTransport` or `LiveKitTransport`.
 
 - Added `watchdog_coroutine()`. This is a watchdog helper for couroutines. So,
   if you have a coroutine that is waiting for a result and that takes a long

scripts/evals/README.md

@@ -49,7 +49,7 @@ python run-release-evals.py -p 07 -a -v
 You can also run evals for a single example (not part of the release set):
 
 ```sh
-python run-eval.py YOUR_EXAMPLE_SCRIPT -a -v
+python run-eval.py -p "A simple math addition" -a -v YOUR_EXAMPLE_SCRIPT
 ```
 
 Your script needs to follow any of the foundation examples pattern.

scripts/evals/eval.py

@@ -104,7 +104,7 @@ class EvalRunner:
                 asyncio.create_task(run_example_pipeline(script_path)),
                 asyncio.create_task(run_eval_pipeline(self, example_file, prompt, eval)),
             ]
-            _, pending = await asyncio.wait(tasks, timeout=10)
+            _, pending = await asyncio.wait(tasks, timeout=90)
             if pending:
                 logger.error(f"ERROR: Eval timeout expired, cancelling pending tasks...")
                 for task in pending:

scripts/evals/run-release-evals.py

@@ -39,6 +39,7 @@ TESTS_07 = [
     # 07 series
     ("07-interruptible.py", PROMPT_SIMPLE_MATH, None),
     ("07-interruptible-cartesia-http.py", PROMPT_SIMPLE_MATH, None),
+    ("07a-interruptible-speechmatics.py", PROMPT_SIMPLE_MATH, None),
     ("07b-interruptible-langchain.py", PROMPT_SIMPLE_MATH, None),
     ("07c-interruptible-deepgram.py", PROMPT_SIMPLE_MATH, None),
     ("07d-interruptible-elevenlabs.py", PROMPT_SIMPLE_MATH, None),