From 06be20eb16fc5de81cb919efadc0eb19f20f3ef5 Mon Sep 17 00:00:00 2001 From: Mark Backman Date: Wed, 9 Apr 2025 14:32:53 -0400 Subject: [PATCH] Fix: Cartesia's spelling feature adds whole word to context --- CHANGELOG.md | 4 ++++ src/pipecat/services/cartesia/tts.py | 1 + 2 files changed, 5 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 56b5da75f..1ba5558ef 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -66,6 +66,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - Updated `daily-python` to 0.17.0 to fix an issue that was preventing to run on older platforms. +- Fixed an issue where `CartesiaTTSService`'s spell feature would result in + the spelled word in the context appearing as "F,O,O,B,A,R" instead of + "FOOBAR". + - Fixed an issue in the Azure TTS services where the language was being set incorrectly. diff --git a/src/pipecat/services/cartesia/tts.py b/src/pipecat/services/cartesia/tts.py index a4d0c3fa4..eb891693d 100644 --- a/src/pipecat/services/cartesia/tts.py +++ b/src/pipecat/services/cartesia/tts.py @@ -166,6 +166,7 @@ class CartesiaTTSService(AudioContextWordTTSService): "output_format": self._settings["output_format"], "language": self._settings["language"], "add_timestamps": add_timestamps, + "use_original_timestamps": True, } return json.dumps(msg)