feat(azure/stt): TrueText post processing option added to STTOptions

[rafallezanko]

https://learn.microsoft.com/en-us/javascript/api/microsoft-cognitiveservices-speech-sdk/propertyid?view=azure-node-latest

SpeechServiceResponse_PostProcessingOption = 39 | A string value specifying which post processing option should be used by service. Allowed values are "TrueText". Added in version 1.7.0

Summary by CodeRabbit

• New Features
  • Added an optional TrueText post‑processing toggle for the Azure speech‑to‑text plugin. When enabled per instance at initialization, transcriptions receive TrueText formatting/cleanup to improve readability and accuracy. Disabled by default and can be turned on for individual speech‑to‑text instances to enhance output quality.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

📝 Walkthrough

Walkthrough

Adds a boolean true_text_post_processing option to the Azure STT plugin: exposed on STT.__init__, stored in STTOptions, and applied in _create_speech_recognizer() by setting the SpeechConfig post-processing option to "TrueText" when enabled.

Changes

Cohort / File(s)	Summary
Azure STT plugin livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/stt.py	Added true_text_post_processing: bool = False to STTOptions; added true_text_post_processing parameter to STT.__init__ and propagated it into STTOptions; updated _create_speech_recognizer() to set SpeechConfig's post-processing option to "TrueText" when the flag is truthy.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Poem

🐇 I added a switch with a joyful hop,
TrueText whispers and cleans each drop.
A tiny flag to guide the stream,
Words made tidy, neat, and gleam. ✨

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 50.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The PR title accurately and specifically describes the main change: adding the TrueText post-processing option to Azure STTOptions, which is the primary focus of the changeset.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing touches

• 📝 Generate docstrings

---

📜 Recent review details

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between f363d24 and c09cfdd.

📒 Files selected for processing (1)

• livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/stt.py

🚧 Files skipped from review as they are similar to previous changes (1)

• livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/stt.py

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

• GitHub Check: unit-tests

_{✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.}

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 0

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/stt.py (1)

407-413: Use the correct PropertyId enum: SpeechServiceResponse_PostProcessingOption instead of PostProcessingOption.

The enum speechsdk.enums.PropertyId.PostProcessingOption does not exist in the Azure Speech SDK (1.43.0+). The correct enum name is SpeechServiceResponse_PostProcessingOption (ID: 4003). The current code will raise an AttributeError at runtime.

Fix

-        speech_config.set_property(speechsdk.enums.PropertyId.PostProcessingOption, "TrueText")
+        speech_config.set_property(
+            speechsdk.enums.PropertyId.SpeechServiceResponse_PostProcessingOption,
+            "TrueText",
+        )

🧹 Nitpick comments (1)

livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/stt.py (1)

83-102: Document the new option in the constructor docstring.

The new public parameter isn’t described yet, which makes the API harder to discover.

📌 Suggested docstring update

@@
         Args:
             phrase_list: List of words or phrases to boost recognition accuracy.
                         Azure will give higher priority to these phrases during recognition.
             explicit_punctuation: Controls punctuation behavior. If True, enables explicit punctuation mode
                         where punctuation marks are added explicitly. If False (default), uses Azure's
                         default punctuation behavior.
+            true_text_post_processing: Enables Azure "TrueText" post-processing in the recognition result.

As per coding guidelines, maintain Google-style docstrings for public APIs.

📜 Review details

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 0722371 and bdf13ad.

⛔ Files ignored due to path filters (1)

• uv.lock is excluded by !**/*.lock

📒 Files selected for processing (1)

• livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/stt.py

🧰 Additional context used

📓 Path-based instructions (1)

**/*.py

📄 CodeRabbit inference engine (AGENTS.md)

**/*.py: Format code with ruff
Run ruff linter and auto-fix issues
Run mypy type checker in strict mode
Maintain line length of 100 characters maximum
Ensure Python 3.9+ compatibility
Use Google-style docstrings

Files:

• livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/stt.py

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)

• GitHub Check: type-check (3.13)
• GitHub Check: type-check (3.9)
• GitHub Check: unit-tests

🔇 Additional comments (2)

livekit-plugins/livekit-plugins-azure/livekit/plugins/azure/stt.py (2)

41-62: LGTM: default-off option is sensible.

The new true_text_post_processing field is a safe, backward-compatible addition.

---

141-157: LGTM: option is correctly propagated into STTOptions.

Wiring looks consistent with the other options.

_{✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.}

[rafallezanko]

Hi @chenghao-mou , can you have a look at the MR? Thank you in advance :)

[chenghao-mou]

/test-stt

[github-actions]

STT Test Results

Status: ✗ Some tests failed

Metric	Count
✓ Passed	22
✗ Failed	1
× Errors	1
→ Skipped	15
▣ Total	39
⏱ Duration	240.1s

Failed Tests

• tests.test_stt::test_stream[livekit.agents.inference]

  stt_factory = <function parameter_factory.<locals>.<lambda> at 0x7fcd92109440>
  request = <FixtureRequest for <Coroutine test_stream[livekit.agents.inference]>>
  
      @pytest.mark.usefixtures("job_process")
      @pytest.mark.parametrize("stt_factory", STTs)
      async def test_stream(stt_factory: Callable[[], STT], request):
          sample_rate = SAMPLE_RATE
          plugin_id = request.node.callspec.id.split("-")[0]
          frames, transcript, _ = await make_test_speech(chunk_duration_ms=10, sample_rate=sample_rate)
    
          # TODO: differentiate missing key vs other errors
          try:
              stt_instance: STT = stt_factory()
          except ValueError as e:
              pytest.skip(f"{plugin_id}: {e}")
    
          async with stt_instance as stt:
              label = f"{stt.model}@{stt.provider}"
              if not stt.capabilities.streaming:
                  pytest.skip(f"{label} does not support streaming")
    
              for attempt in range(MAX_RETRIES):
                  try:
                      state = {"closing": False}
    
                      async def _stream_input(
                          frames: list[rtc.AudioFrame], stream: RecognizeStream, state: dict = state
                      ):
                          for frame in frames:
                              stream.push_frame(frame)
                              await asyncio.sleep(0.005)
    
                          stream.end_input()
                          state["closing"] = True
    
                      async def _stream_output(stream: RecognizeStream, state: dict = state):
                          text = ""
                          # make sure the events are sent in the right order
                          recv_start, recv_end = False, True
                          start_time = time.time()
                          got_final_transcript = False
    
                          async for event in stream:
                              if event.type == agents.stt.SpeechEventType.START_OF_SPEECH:
  

• tests.test_stt::test_stream[livekit.plugins.aws]

  def finalizer() -> None:
          """Yield again, to finalize."""
    
          async def async_finalizer() -> None:
              try:
                  await gen_obj.__anext__()  # type: ignore[union-attr]
              except StopAsyncIteration:
                  pass
              else:
                  msg = "Async generator fixture didn't stop."
                  msg += "Yield only once."
                  raise ValueError(msg)
    
          task = _create_task_in_context(event_loop, async_finalizer(), context)
  >       event_loop.run_until_complete(task)
  
  .venv/lib/python3.12/site-packages/pytest_asyncio/plugin.py:347: 
  _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
  
  self = <_UnixSelectorEventLoop running=False closed=True debug=False>
  future = <Task finished name='Task-122' coro=<_wrap_asyncgen_fixture.<locals>._asyncgen_fixture_wrapper.<locals>.finalizer.<loc... File "/home/runner/work/agents/agents/.venv/lib/python3.12/site-packages/smithy_http/aio/crt.py", line 104, in chunks>
  
      def run_until_complete(self, future):
          """Run until the Future is done.
    
          If the argument is a coroutine, it is wrapped in a Task.
    
          WARNING: It would be disastrous to call run_until_complete()
          with the same coroutine twice -- it would wrap it in two
          different Tasks and that can't be good.
    
          Return the Future's result, or raise its exception.
          """
          self._check_closed()
          self._check_running()
    
          new_task = not futures.isfuture(future)
          future = tasks.ensure_future(future, loop=self)
          if new_task:
              # An exception is raised if the future didn't complete, so there
              # is no need to log the "destroy pending task" message
              future._log_destroy_pending = False
    
          future.add_done_callback(_run_until_complete_cb)
          try:
              self.run_forever()
          except:
              if new_task and future.done() and not future.canc
  

Skipped Tests

Test	Reason
tests.test_stt::test_recognize[livekit.plugins.assemblyai]	universal-streaming-english@AssemblyAI does not support batch recognition
tests.test_stt::test_recognize[livekit.plugins.speechmatics]	unknown@Speechmatics does not support batch recognition
tests.test_stt::test_recognize[livekit.plugins.fireworksai]	unknown@FireworksAI does not support batch recognition
tests.test_stt::test_recognize[livekit.plugins.nvidia]	unknown@unknown does not support batch recognition
tests.test_stt::test_recognize[livekit.plugins.aws]	unknown@Amazon Transcribe does not support batch recognition
tests.test_stt::test_recognize[livekit.plugins.cartesia]	ink-whisper@Cartesia does not support batch recognition
tests.test_stt::test_recognize[livekit.plugins.soniox]	stt-rt-v3@Soniox does not support batch recognition
tests.test_stt::test_recognize[livekit.plugins.deepgram.STTv2]	flux-general-en@Deepgram does not support batch recognition
tests.test_stt::test_recognize[livekit.plugins.gradium.STT]	unknown@Gradium does not support batch recognition
tests.test_stt::test_recognize[livekit.agents.inference]	unknown@livekit does not support batch recognition
tests.test_stt::test_recognize[livekit.plugins.azure]	unknown@Azure STT does not support batch recognition
tests.test_stt::test_stream[livekit.plugins.elevenlabs]	scribe_v1@ElevenLabs does not support streaming
tests.test_stt::test_stream[livekit.plugins.fal]	Wizper@Fal does not support streaming
tests.test_stt::test_stream[livekit.plugins.mistralai]	voxtral-mini-latest@MistralAI does not support streaming
tests.test_stt::test_stream[livekit.plugins.openai]	[email protected] does not support streaming

---

Triggered by workflow run #378

[chenghao-mou]

LGTM. Confirmed it removed disfluencies when enabled.

But the uv.lock change seems unnecessary; we should drop it.

[rafallezanko]

Good, the uv.lock change is already merged in a master branch. I've synced my branch and the change disappeared.