Merge pull request #4424 from pipecat-ai/mb/revert-elevenlabs-tts-alignment

fix(elevenlabs): only use normalizedAlignment when pronunciation dict is set
2026-05-06 08:27:25 -04:00
parent 3722ee223c 2620e76dab
commit eda98fb13f
3 changed files with 172 additions and 18 deletions
--- a/changelog/4424.fixed.md
+++ b/changelog/4424.fixed.md
@@ -0,0 +1 @@
+- Fixed `ElevenLabsTTSService` and `ElevenLabsHttpTTSService` writing romanized/normalized text to the LLM context. With non-Latin input (e.g., Chinese), the assistant transcript was getting populated with pinyin (`Ni Hao !` instead of `你好！`), which then degraded subsequent LLM turns. The services now consume `alignment` by default and only switch to `normalizedAlignment` / `normalized_alignment` when `pronunciation_dictionary_locators` is configured (where `alignment` has overlapping restarts that produce duplicated/garbled words, per #4316). Both fields are read with preferred-with-fallback semantics since each is nullable per the API schema.
				`@@ -0,0 +1 @@`
				- Fixed `ElevenLabsTTSService` and `ElevenLabsHttpTTSService` writing romanized/normalized text to the LLM context. With non-Latin input (e.g., Chinese), the assistant transcript was getting populated with pinyin (`Ni Hao !` instead of `你好！`), which then degraded subsequent LLM turns. The services now consume `alignment` by default and only switch to `normalizedAlignment` / `normalized_alignment` when `pronunciation_dictionary_locators` is configured (where `alignment` has overlapping restarts that produce duplicated/garbled words, per #4316). Both fields are read with preferred-with-fallback semantics since each is nullable per the API schema.