Add isolated Gemini dictation route with native personal vocabulary

2026-10-25 00:19:22 -07:00
parent 8746be24ce
commit 035daa177d
3 changed files with 54 additions and 1 deletions
@@ -0,0 +1,49 @@
+"""Add native vocabulary only to explicitly opted-in Gemini transcription calls."""
+import json
+from pathlib import Path
+
+VOCABULARY = Path('/etc/litellm/personal-vocabulary.json')
+
+
+def vocabulary(path=VOCABULARY):
+    words = json.loads(path.read_text())
+    if not isinstance(words, list) or not 1 <= len(words) <= 100:
+        raise ValueError('Personal vocabulary must contain 1–100 terms')
+    if any(not isinstance(word, str) or not word.strip() or len(word) > 100 for word in words):
+        raise ValueError('Invalid personal vocabulary term')
+    return list(dict.fromkeys(words))
+
+
+def install():
+    from litellm.llms.gemini.audio_transcription.transformation import GeminiAudioTranscriptionConfig
+    original = GeminiAudioTranscriptionConfig.transform_audio_transcription_request
+    if getattr(original, '_personal_vocabulary_patch', False):
+        return
+
+    def transform(self, model, audio_file, optional_params, litellm_params):
+        enabled = optional_params.get('personal_vocabulary') is True
+        if not enabled:
+            return original(self, model, audio_file, optional_params, litellm_params)
+        if model.removeprefix('gemini/') != 'gemini-3.5-transcribe':
+            raise ValueError('Personal vocabulary is restricted to Gemini 3.5 Transcribe')
+        if optional_params.get('timestamp_granularities') or optional_params.get('response_format') not in (None, 'json', 'text'):
+            raise ValueError('Personal dictation does not support timestamps or diarization')
+        clean = {key: value for key, value in optional_params.items() if key != 'personal_vocabulary'}
+        result = original(self, model, audio_file, clean, litellm_params)
+        config = result.data.setdefault('generation_config', {}).setdefault('transcription_config', {})
+        # Fail closed if a future LiteLLM version enables conflicting features by default.
+        if config.get('mode'):
+            raise ValueError('Unexpected Gemini transcription mode')
+        config['custom_vocabulary'] = vocabulary()
+        return result
+
+    transform._personal_vocabulary_patch = True
+    GeminiAudioTranscriptionConfig.transform_audio_transcription_request = transform
+
+
+if __name__ == '__main__':
+    import sys
+    from litellm import run_server
+    install()
+    sys.argv[0] = 'litellm'
+    sys.exit(run_server())