diff --git a/CHANGELOG.md b/CHANGELOG.md
index 2dafdfa26..9c4ee5eaf 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added support for Chirp voices in `GoogleTTSService`.
+
 - Added `on_user_turn_audio_data` and `on_bot_turn_audio_data` to
   `AudioBufferProcessor`. This gives the ability to grab the audio of only that
   turn for both the user and the bot.
diff --git a/src/pipecat/services/google/google.py b/src/pipecat/services/google/google.py
index 1d914a9bb..009fd772f 100644
--- a/src/pipecat/services/google/google.py
+++ b/src/pipecat/services/google/google.py
@@ -1448,10 +1448,13 @@ class GoogleTTSService(TTSService):
         try:
             await self.start_ttfb_metrics()
 
+            # Check if the voice is a Chirp voice (including Chirp 3) or Journey voice
+            is_chirp_voice = "chirp" in self._voice_id.lower()
             is_journey_voice = "journey" in self._voice_id.lower()
 
             # Create synthesis input based on voice_id
-            if is_journey_voice:
+            if is_chirp_voice or is_journey_voice:
+                # Chirp and Journey voices don't support SSML, use plain text
                 synthesis_input = texttospeech_v1.SynthesisInput(text=text)
             else:
                 ssml = self._construct_ssml(text)