diff --git a/studio/backend/requirements/extras.txt b/studio/backend/requirements/extras.txt
index 170b1c9ec8..d783975a4f 100644
--- a/studio/backend/requirements/extras.txt
+++ b/studio/backend/requirements/extras.txt
@@ -26,8 +26,9 @@ omegaconf
 einx
 pyloudnorm
 openai-whisper
-# uroman                         # 4.0 MB - romanization, no imports found
-# MeCab                          # 19.9 MB - Japanese tokenizer, no imports found
+uroman                           # 4.0 MB - used for Outetts.
+MeCab                            # 19.9 MB - used for Outetts.
+inflect                          # number-to-words, required by OuteTTS
 loguru
 flatten_dict
 ffmpy
diff --git a/studio/backend/utils/models/model_config.py b/studio/backend/utils/models/model_config.py
index aaf15994be..13f1b5febf 100644
--- a/studio/backend/utils/models/model_config.py
+++ b/studio/backend/utils/models/model_config.py
@@ -630,7 +630,10 @@ _AUDIO_TOKEN_PATTERNS = {
     "whisper": lambda tokens: "<|startoftranscript|>" in tokens,
     "audio_vlm": lambda tokens: "<audio_soft_token>" in tokens,
     "bicodec": lambda tokens: any(t.startswith("<|bicodec_") for t in tokens),
-    "dac": lambda tokens: "<|audio_start|>" in tokens and "<|audio_end|>" in tokens,
+    "dac": lambda tokens: "<|audio_start|>" in tokens
+    and "<|audio_end|>" in tokens
+    and "<|text_start|>" in tokens
+    and "<|text_end|>" in tokens,
     "snac": lambda tokens: sum(1 for t in tokens if t.startswith("<custom_token_"))
     > 10000,
 }