From f7d9f32b0fcd560fc3819d9c04650e18c14ae0cd Mon Sep 17 00:00:00 2001
From: Mark Backman <mark@daily.co>
Date: Wed, 27 Aug 2025 13:34:28 -0400
Subject: [PATCH] Cartesia: update speed InputParam

---
 CHANGELOG.md                         |  4 ++++
 src/pipecat/services/cartesia/tts.py | 10 +++++-----
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7aade22d1..9cbc09712 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -87,6 +87,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
+- Updated `CartesiaTTSService` and `CartesiaHttpTTSService` to align with
+  Cartesia's changes for the `speed` parameter. It now takes only an enum of
+  `slow`, `normal`, or `fast`.
+
 - Added support to `AWSBedrockLLMService` for setting authentication
   credentials through environment variables.
 
diff --git a/src/pipecat/services/cartesia/tts.py b/src/pipecat/services/cartesia/tts.py
index 53208b53f..f8f148a38 100644
--- a/src/pipecat/services/cartesia/tts.py
+++ b/src/pipecat/services/cartesia/tts.py
@@ -10,7 +10,7 @@ import base64
 import json
 import uuid
 import warnings
-from typing import AsyncGenerator, List, Optional, Union
+from typing import AsyncGenerator, List, Literal, Optional, Union
 
 from loguru import logger
 from pydantic import BaseModel, Field
@@ -101,7 +101,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
 
         Parameters:
             language: Language to use for synthesis.
-            speed: Voice speed control (string or float).
+            speed: Voice speed control.
             emotion: List of emotion controls.
 
                 .. deprecated:: 0.0.68
@@ -109,7 +109,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
         """
 
         language: Optional[Language] = Language.EN
-        speed: Optional[Union[str, float]] = ""
+        speed: Optional[Literal["slow", "normal", "fast"]] = None
         emotion: Optional[List[str]] = []
 
     def __init__(
@@ -478,7 +478,7 @@ class CartesiaHttpTTSService(TTSService):
 
         Parameters:
             language: Language to use for synthesis.
-            speed: Voice speed control (string or float).
+            speed: Voice speed control.
             emotion: List of emotion controls.
 
                 .. deprecated:: 0.0.68
@@ -486,7 +486,7 @@ class CartesiaHttpTTSService(TTSService):
         """
 
         language: Optional[Language] = Language.EN
-        speed: Optional[Union[str, float]] = ""
+        speed: Optional[Literal["slow", "normal", "fast"]] = None
         emotion: Optional[List[str]] = Field(default_factory=list)
 
     def __init__(