Merge pull request #1044 from pipecat-ai/mb/elevenlabs-http-fix-voice-settings

Fixed a type error when using voice_settings in ElevenLabsHttpTTSService

CHANGELOG.md

@@ -5,6 +5,12 @@ 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]
+
+### Fixed
+
+- Fixed a type error when using `voice_settings` in `ElevenLabsHttpTTSService`.
+
 ## [0.0.53] - 2025-01-18
 
 ### Added

src/pipecat/services/elevenlabs.py

@@ -524,13 +524,13 @@ class ElevenLabsHttpTTSService(TTSService):
 
         url = f"{self._base_url}/v1/text-to-speech/{self._voice_id}/stream"
 
-        payload = {
+        payload: Dict[str, Union[str, Dict[str, Union[float, bool]]]] = {
             "text": text,
             "model_id": self._model_name,
         }
 
         if self._voice_settings:
-            payload["voice_settings"] = json.dumps(self._voice_settings)
+            payload["voice_settings"] = self._voice_settings
 
         if self._settings["language"]:
             payload["language_code"] = self._settings["language"]