Add isolated Gemini dictation route with native personal vocabulary

servers/tools-pve/litellm/compose.yaml

@@ -48,10 +48,12 @@ services:
     volumes:
       - ./models.yaml:/etc/litellm/models.yaml:ro
       - ./render_config.py:/etc/litellm/render_config.py:ro
+      - ./personal_transcription.py:/etc/litellm/personal_transcription.py:ro
+      - /opt/litellm/personal-vocabulary.json:/etc/litellm/personal-vocabulary.json:ro
       - oauth:/tokens
     entrypoint: [/bin/sh, -c]
     command:
-      - 'python /etc/litellm/render_config.py && exec litellm --config /tmp/litellm.yaml --host 0.0.0.0 --port 4000 --num_workers 1'
+      - 'python /etc/litellm/render_config.py && exec python /etc/litellm/personal_transcription.py --config /tmp/litellm.yaml --host 0.0.0.0 --port 4000 --num_workers 1'
     healthcheck:
       test: [CMD, python, -c, 'import urllib.request; urllib.request.urlopen("http://127.0.0.1:4000/health/liveliness", timeout=5)']
       interval: 30s

servers/tools-pve/litellm/personal_transcription.py

@@ -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())

servers/tools-pve/litellm/render_config.py

@@ -56,6 +56,8 @@ def build_config(catalog, env, exists):
             add(alias, 'openai/' + model, 'ZENMUX_SUBSCRIPTION_API_KEY',
                 api_base='https://zenmux.ai/api/v1', max_retries=0)
     if env.get('GOOGLE_AI_STUDIO_API_KEY'):
+        add('gemini-transcribe-personal', 'gemini/gemini-3.5-transcribe',
+            'GOOGLE_AI_STUDIO_API_KEY', personal_vocabulary=True)
         for alias, model in catalog['google_ai_studio'].items():
             add(alias, 'gemini/' + model, 'GOOGLE_AI_STUDIO_API_KEY')
     if env.get('VERTEXAI_ENABLED', '').lower() == 'true' and env.get('VERTEXAI_PROJECT'):