diff --git a/examples/offline_inference/voxtral_tts/README.md b/examples/offline_inference/voxtral_tts/README.md
index 7e0f84f2c..f552fd165 100644
--- a/examples/offline_inference/voxtral_tts/README.md
+++ b/examples/offline_inference/voxtral_tts/README.md
@@ -6,37 +6,44 @@ When `mistral_common` has `SpeechRequest` support, prompt token IDs are built vi
 
 ## Usage Examples
 
-```bash
-# Basic single-prompt with reference audio
-python3 examples/offline_inference/voxtral_tts/end2end.py \
-    --write-audio \
-    --model mistralai/tts-model \
-    --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?" \
-    --audio-path path/to/reference_audio.wav
 
-# 32 replicate prompts with reference audio
+```bash
+# Basic single-prompt with cheerful_female voice preset
 python3 examples/offline_inference/voxtral_tts/end2end.py \
-    --num-prompts 32 --write-audio \
+    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
+    --write-audio --voice cheerful_female \
     --model mistralai/tts-model \
-    --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?" \
-    --audio-path path/to/reference_audio.wav
+    --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
+
+# 32 replicate prompts with cheerful_female voice preset
+python3 examples/offline_inference/voxtral_tts/end2end.py \
+    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
+    --num-prompts 32 --write-audio --voice cheerful_female \
+    --model mistralai/tts-model \
+    --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
+
+# Streaming with neutral_female voice preset
+python3 examples/offline_inference/voxtral_tts/end2end.py \
+    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
+    --streaming --write-audio --voice neutral_female \
+    --model mistralai/tts-model \
+    --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
+
+# 32 prompts, 8 concurrent requests per wave, streaming with neutral_female voice
+python3 examples/offline_inference/voxtral_tts/end2end.py \
+    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
+    --num-prompts 32 --concurrency 8 --streaming --write-audio --voice neutral_female \
+    --model mistralai/tts-model \
+    --text "That eerie silence after the first storm was just the calm before another round of chaos, wasn't it?"
 
 # Short debug prompt with reference audio
+# Note: Reference audio capability is not yet released.
 python3 examples/offline_inference/voxtral_tts/end2end.py \
+    --stage-configs-path vllm_omni/model_executor/stage_configs/voxtral_tts.yaml \
     --write-audio \
     --model mistralai/tts-model \
     --text "This is a test message." \
     --audio-path path/to/reference_audio.wav
-
-# Streaming with neutral_female voice preset
-python3 examples/offline_inference/voxtral_tts/end2end.py \
-    --streaming --write-audio --voice neutral_female \
-    --model mistralai/tts-model
-
-# 32 prompts, 8 concurrent requests per wave, streaming with casual_male voice
-python3 examples/offline_inference/voxtral_tts/end2end.py \
-    --num-prompts 32 --concurrency 8 --streaming --write-audio --voice casual_male \
-    --model mistralai/tts-model
 ```
 
 ## Arguments
@@ -47,7 +54,7 @@ python3 examples/offline_inference/voxtral_tts/end2end.py \
 | `--text TEXT` | Text to synthesize (default: `"This is a test message."`) |
 | `--audio-path PATH` | Path to reference audio file for voice cloning |
 | `--output-dir DIR` | Directory to write output WAV files (default: `output_audio`) |
-| `--stage-configs-path PATH` | Path to stage configs YAML (auto-resolved from model if not set) |
+| `--stage-configs-path PATH` | Path to stage configs YAML (currently it must be set for VoxtralTTS) |
 | `--num-prompts N` | Number of replicate prompts to run for measuring performance (default: 1) |
 | `--streaming` | Use streaming generation via `AsyncOmni` (default: blocking `Omni`) |
 | `--concurrency N` | Max concurrent requests per wave (must be used with `--streaming`, must evenly divide `--num-prompts`) |
diff --git a/examples/offline_inference/voxtral_tts/end2end.py b/examples/offline_inference/voxtral_tts/end2end.py
index 569b5f6f3..d3052e5ca 100644
--- a/examples/offline_inference/voxtral_tts/end2end.py
+++ b/examples/offline_inference/voxtral_tts/end2end.py
@@ -208,7 +208,7 @@ def run_non_streaming(inputs, sampling_params_list, model_name, args, output_dir
     output_audio_dur = 0.0
 
     for batch_idx, o in enumerate(outputs):
-        audio_tensor = torch.cat(o.request_output[0].outputs[0].multimodal_output["audio"])
+        audio_tensor = torch.cat(o.multimodal_output["audio"])
         audio_array = audio_tensor.tolist()
         output_audio_dur += float(len(audio_array)) / 24000
         if args.write_audio: