From 1e3fa4a9c7fa94aa4957909dffc0d9c15d5a4b9d Mon Sep 17 00:00:00 2001
From: Kwindla Hultman Kramer <kwindla@daily.co>
Date: Sat, 14 Jun 2025 17:41:44 -0400
Subject: [PATCH 1/2] fix groq wav file header parsing

---
 src/pipecat/services/groq/tts.py | 38 ++++++++++++++++++--------------
 1 file changed, 22 insertions(+), 16 deletions(-)

diff --git a/src/pipecat/services/groq/tts.py b/src/pipecat/services/groq/tts.py
index 6f73b1629..33fd3ce34 100644
--- a/src/pipecat/services/groq/tts.py
+++ b/src/pipecat/services/groq/tts.py
@@ -4,6 +4,8 @@
 # SPDX-License-Identifier: BSD 2-Clause License
 #
 
+import io
+import wave
 from typing import AsyncGenerator, Optional
 
 from loguru import logger
@@ -78,22 +80,26 @@ class GroqTTSService(TTSService):
         await self.start_ttfb_metrics()
         yield TTSStartedFrame()
 
-        response = await self._client.audio.speech.create(
-            model=self._model_name,
-            voice=self._voice_id,
-            response_format=self._output_format,
-            input=text,
-        )
+        try:
+            response = await self._client.audio.speech.create(
+                model=self._model_name,
+                voice=self._voice_id,
+                response_format=self._output_format,
+                input=text,
+            )
 
-        async for data in response.iter_bytes():
-            if measuring_ttfb:
-                await self.stop_ttfb_metrics()
-                measuring_ttfb = False
-            # remove wav header if present
-            if data.startswith(b"RIFF"):
-                data = data[44:]
-                if len(data) == 0:
-                    continue
-            yield TTSAudioRawFrame(data, self.sample_rate, 1)
+            async for data in response.iter_bytes():
+                if measuring_ttfb:
+                    await self.stop_ttfb_metrics()
+                    measuring_ttfb = False
+
+                with wave.open(io.BytesIO(data)) as w:
+                    channels = w.getnchannels()
+                    frame_rate = w.getframerate()
+                    num_frames = w.getnframes()
+                    bytes = w.readframes(num_frames)
+                    yield TTSAudioRawFrame(bytes, frame_rate, channels)
+        except Exception as e:
+            logger.error(f"{self} exception: {e}")
 
         yield TTSStoppedFrame()

From fe16ed3c73882c42e1cbbc1020757cad15112bc0 Mon Sep 17 00:00:00 2001
From: Kwindla Hultman Kramer <kwindla@daily.co>
Date: Sun, 15 Jun 2025 10:49:40 -0700
Subject: [PATCH 2/2] added changelog entry

---
 CHANGELOG.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 5c8648272..cfbeb5010 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- Fixed an issue with `GroqTTSService` where it was not properly parsing the
+  WAV file header.
+
 - Fixed an issue with `GoogleSTTService` where it was constantly reconnecting 
   before starting to receive audio from the user.