vllm - ✅(Solved) Fix [Bug]: Missing `soundfile` dependency breaks audio transcription [1 pull requests, 1 comments, 2 participants]

vllm2026-04-10 03:18:13

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

vllm-project/vllm#39472•Fetched 2026-04-11 06:13:26

View on GitHub

Comments

Participants

Timeline

Reactions

Author

tunglinwood

Participants

ianliuy

tunglinwood

Timeline (top)

referenced ×3commented ×1cross-referenced ×1labeled ×1

Error Message

The /v1/audio/transcriptions endpoint returns {"error": "Invalid or unsupported audio file."} for valid audio files when soundfile is not installed. 2. When soundfile is missing, it becomes a PlaceholderModule. The except soundfile.LibsndfileError in load_audio() (vllm/multimodal/media/audio.py:142) then raises an ImportError when evaluating the exception type. This ImportError is not caught by the except clause and bubbles up to speech_to_text.py:200, where it gets caught by a generic except Exception and replaced with the misleading "Invalid or unsupported audio file." message.

Root Cause

soundfile is only in requirements/test.in, not in requirements/common.txt. A normal uv pip install -e . won't install it.
When soundfile is missing, it becomes a PlaceholderModule. The except soundfile.LibsndfileError in load_audio() (vllm/multimodal/media/audio.py:142) then raises an ImportError when evaluating the exception type. This ImportError is not caught by the except clause and bubbles up to speech_to_text.py:200, where it gets caught by a generic except Exception and replaced with the misleading "Invalid or unsupported audio file." message.

Fix Action

Fix / Workaround

============================== CPU Info

架构： x86_64 CPU 运行模式： 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual 字节序： Little Endian CPU: 64 在线 CPU 列表： 0-63 厂商 ID： GenuineIntel BIOS Vendor ID: Intel(R) Corporation 型号名称： Intel(R) Xeon(R) Platinum 8350C CPU @ 2.60GHz BIOS Model name: Intel(R) Xeon(R) Platinum 8350C CPU @ 2.60GHz CPU 系列： 6 型号： 106 每个核的线程数： 1 每个座的核数： 32 座： 2 步进： 6 CPU 最大 MHz： 3500.0000 CPU 最小 MHz： 800.0000 BogoMIPS： 5200.00 标记： fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities 虚拟化： VT-x L1d 缓存： 3 MiB (64 instances) L1i 缓存： 2 MiB (64 instances) L2 缓存： 80 MiB (64 instances) L3 缓存： 96 MiB (2 instances) NUMA 节点： 2 NUMA 节点0 CPU： 0-31 NUMA 节点1 CPU： 32-63 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Indirect target selection: Vulnerable Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT disabled Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Not affected

PR fix notes

PR #39473: fix: handle ImportError in load_audio

Repository: vllm-project/vllm
Author: ianliuy
State: closed | merged: True
Link: https://github.com/vllm-project/vllm/pull/39473

Description (problem / solution / changelog)

Summary

Fixes #39472

When soundfile is not installed, load_audio() crashes with a misleading "Invalid or unsupported audio file." error instead of falling back to pyav.

Root Cause

soundfile is only in requirements/test.in and extras_require["audio"], not in requirements/common.txt normal install skips it
Without soundfile, it becomes a PlaceholderModule. The except soundfile.LibsndfileError clause in load_audio() triggers PlaceholderModule.__getattr__("LibsndfileError"), raising ImportError during exception handler evaluation
The pyav fallback never executes; speech_to_text.py's except Exception swallows the ImportError and replaces it with a misleading client error

Changes

`requirements/common.txt`

Add soundfile as a default dependency (alongside pillow, opencv-python-headless)

`vllm/multimodal/media/audio.py`

Add except ImportError before except soundfile.LibsndfileError in load_audio() Python evaluates except clauses top-to-bottom, so ImportError matches first and soundfile.LibsndfileError is never evaluated when soundfile is a PlaceholderModule
Improve error message to suggest installing both soundfile and av

Edge Cases

soundfile installed, resampy missing ImportError caught pyav fallback
Both soundfile and av missing clear error: pip install soundfile av
soundfile installed, unsupported format LibsndfileError pyav fallback

Changed files

vllm/multimodal/media/audio.py (modified, +19/-8)

Code Example

Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 12.3.0-1ubuntu1~22.04.3) 12.3.0
Clang version                : 14.0.0-1ubuntu1.1
CMake version                : version 4.2.3
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu128
Is debug build               : False
CUDA used to build PyTorch   : 12.8
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.12 (main, Dec  9 2025, 19:02:36) [Clang 21.1.4 ] (64-bit runtime)
Python platform              : Linux-6.8.0-101-generic-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.9.86
CUDA_MODULE_LOADING set to   :
GPU models and configuration :
GPU 0: NVIDIA L20
GPU 1: NVIDIA L20
GPU 2: NVIDIA L20
GPU 3: NVIDIA L20
GPU 4: NVIDIA L20
GPU 5: NVIDIA L20
GPU 6: NVIDIA L20
GPU 7: NVIDIA L20

Nvidia driver version        : 595.58.03
cuDNN version                : Could not collect
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
架构：                                   x86_64
CPU 运行模式：                           32-bit, 64-bit
Address sizes:                           52 bits physical, 57 bits virtual
字节序：                                 Little Endian
CPU:                                     64
在线 CPU 列表：                          0-63
厂商 ID：                                GenuineIntel
BIOS Vendor ID:                          Intel(R) Corporation
型号名称：                               Intel(R) Xeon(R) Platinum 8350C CPU @ 2.60GHz
BIOS Model name:                         Intel(R) Xeon(R) Platinum 8350C CPU @ 2.60GHz
CPU 系列：                               6
型号：                                   106
每个核的线程数：                         1
每个座的核数：                           32
座：                                     2
步进：                                   6
CPU 最大 MHz：                           3500.0000
CPU 最小 MHz：                           800.0000
BogoMIPS：                               5200.00
标记：                                   fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
虚拟化：                                 VT-x
L1d 缓存：                               3 MiB (64 instances)
L1i 缓存：                               2 MiB (64 instances)
L2 缓存：                                80 MiB (64 instances)
L3 缓存：                                96 MiB (2 instances)
NUMA 节点：                              2
NUMA 节点0 CPU：                         0-31
NUMA 节点1 CPU：                         32-63
Vulnerability Gather data sampling:      Mitigation; Microcode
Vulnerability Indirect target selection: Vulnerable
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Mitigation; Clear CPU buffers; SMT disabled
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.6
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-cufile-cu12==1.13.1.3
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cutlass-dsl==4.4.1
[pip3] nvidia-cutlass-dsl-libs-base==4.4.1
[pip3] nvidia-ml-py==13.590.48
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pyzmq==27.1.0
[pip3] torch==2.10.0
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0
[pip3] torchvision==0.25.0
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.1rc1.dev174+g0bd5d3d88 (git sha: 0bd5d3d88)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    NIC0    CPU AffinityNUMA Affinity   GPU NUMA ID
GPU0     X      PXB     PXB     PXB     SYS     SYS     SYS     SYS     NODE    0-31    0  N/A
GPU1    PXB      X      PXB     PXB     SYS     SYS     SYS     SYS     NODE    0-31    0  N/A
GPU2    PXB     PXB      X      PIX     SYS     SYS     SYS     SYS     NODE    0-31    0  N/A
GPU3    PXB     PXB     PIX      X      SYS     SYS     SYS     SYS     NODE    0-31    0  N/A
GPU4    SYS     SYS     SYS     SYS      X      PXB     PXB     PXB     SYS     32-63   1  N/A
GPU5    SYS     SYS     SYS     SYS     PXB      X      PXB     PXB     SYS     32-63   1  N/A
GPU6    SYS     SYS     SYS     SYS     PXB     PXB      X      PIX     SYS     32-63   1  N/A
GPU7    SYS     SYS     SYS     SYS     PXB     PXB     PIX      X      SYS     32-63   1  N/A
NIC0    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS      X

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

NIC Legend:

  NIC0: ibp65s0

==============================
     Environment Variables
==============================
LD_LIBRARY_PATH=/root/.microsandbox/lib:/root/.local/lib:/root/.microsandbox/lib:/root/.local/lib:/usr/local/cuda/lib64:
MKL_THREADING_LAYER=GNU
MKL_SERVICE_FORCE_INTEL=1
CUDA_HOME=/usr/local/cuda-12.9
CUDA_HOME=/usr/local/cuda-12.9
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

RAW_BUFFERClick to expand / collapse

Your current environment

<details> <summary>The output of <code>python collect_env.py</code></summary>

Collecting environment information...
==============================
        System Info
==============================
OS                           : Ubuntu 22.04.5 LTS (x86_64)
GCC version                  : (Ubuntu 12.3.0-1ubuntu1~22.04.3) 12.3.0
Clang version                : 14.0.0-1ubuntu1.1
CMake version                : version 4.2.3
Libc version                 : glibc-2.35

==============================
       PyTorch Info
==============================
PyTorch version              : 2.10.0+cu128
Is debug build               : False
CUDA used to build PyTorch   : 12.8
ROCM used to build PyTorch   : N/A

==============================
      Python Environment
==============================
Python version               : 3.12.12 (main, Dec  9 2025, 19:02:36) [Clang 21.1.4 ] (64-bit runtime)
Python platform              : Linux-6.8.0-101-generic-x86_64-with-glibc2.35

==============================
       CUDA / GPU Info
==============================
Is CUDA available            : True
CUDA runtime version         : 12.9.86
CUDA_MODULE_LOADING set to   :
GPU models and configuration :
GPU 0: NVIDIA L20
GPU 1: NVIDIA L20
GPU 2: NVIDIA L20
GPU 3: NVIDIA L20
GPU 4: NVIDIA L20
GPU 5: NVIDIA L20
GPU 6: NVIDIA L20
GPU 7: NVIDIA L20

Nvidia driver version        : 595.58.03
cuDNN version                : Could not collect
HIP runtime version          : N/A
MIOpen runtime version       : N/A
Is XNNPACK available         : True

==============================
          CPU Info
==============================
架构：                                   x86_64
CPU 运行模式：                           32-bit, 64-bit
Address sizes:                           52 bits physical, 57 bits virtual
字节序：                                 Little Endian
CPU:                                     64
在线 CPU 列表：                          0-63
厂商 ID：                                GenuineIntel
BIOS Vendor ID:                          Intel(R) Corporation
型号名称：                               Intel(R) Xeon(R) Platinum 8350C CPU @ 2.60GHz
BIOS Model name:                         Intel(R) Xeon(R) Platinum 8350C CPU @ 2.60GHz
CPU 系列：                               6
型号：                                   106
每个核的线程数：                         1
每个座的核数：                           32
座：                                     2
步进：                                   6
CPU 最大 MHz：                           3500.0000
CPU 最小 MHz：                           800.0000
BogoMIPS：                               5200.00
标记：                                   fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect wbnoinvd dtherm ida arat pln pts vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities
虚拟化：                                 VT-x
L1d 缓存：                               3 MiB (64 instances)
L1i 缓存：                               2 MiB (64 instances)
L2 缓存：                                80 MiB (64 instances)
L3 缓存：                                96 MiB (2 instances)
NUMA 节点：                              2
NUMA 节点0 CPU：                         0-31
NUMA 节点1 CPU：                         32-63
Vulnerability Gather data sampling:      Mitigation; Microcode
Vulnerability Indirect target selection: Vulnerable
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Mitigation; Clear CPU buffers; SMT disabled
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

==============================
Versions of relevant libraries
==============================
[pip3] flashinfer-python==0.6.6
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.8.4.1
[pip3] nvidia-cuda-cupti-cu12==12.8.90
[pip3] nvidia-cuda-nvrtc-cu12==12.8.93
[pip3] nvidia-cuda-runtime-cu12==12.8.90
[pip3] nvidia-cudnn-cu12==9.10.2.21
[pip3] nvidia-cudnn-frontend==1.18.0
[pip3] nvidia-cufft-cu12==11.3.3.83
[pip3] nvidia-cufile-cu12==1.13.1.3
[pip3] nvidia-curand-cu12==10.3.9.90
[pip3] nvidia-cusolver-cu12==11.7.3.90
[pip3] nvidia-cusparse-cu12==12.5.8.93
[pip3] nvidia-cusparselt-cu12==0.7.1
[pip3] nvidia-cutlass-dsl==4.4.1
[pip3] nvidia-cutlass-dsl-libs-base==4.4.1
[pip3] nvidia-ml-py==13.590.48
[pip3] nvidia-nccl-cu12==2.27.5
[pip3] nvidia-nvjitlink-cu12==12.8.93
[pip3] nvidia-nvshmem-cu12==3.4.5
[pip3] nvidia-nvtx-cu12==12.8.90
[pip3] pyzmq==27.1.0
[pip3] torch==2.10.0
[pip3] torch_c_dlpack_ext==0.1.5
[pip3] torchaudio==2.10.0
[pip3] torchvision==0.25.0
[pip3] transformers==4.57.6
[pip3] triton==3.6.0
[conda] Could not collect

==============================
         vLLM Info
==============================
ROCM Version                 : Could not collect
vLLM Version                 : 0.18.1rc1.dev174+g0bd5d3d88 (git sha: 0bd5d3d88)
vLLM Build Flags:
  CUDA Archs: Not Set; ROCm: Disabled
GPU Topology:
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    NIC0    CPU AffinityNUMA Affinity   GPU NUMA ID
GPU0     X      PXB     PXB     PXB     SYS     SYS     SYS     SYS     NODE    0-31    0  N/A
GPU1    PXB      X      PXB     PXB     SYS     SYS     SYS     SYS     NODE    0-31    0  N/A
GPU2    PXB     PXB      X      PIX     SYS     SYS     SYS     SYS     NODE    0-31    0  N/A
GPU3    PXB     PXB     PIX      X      SYS     SYS     SYS     SYS     NODE    0-31    0  N/A
GPU4    SYS     SYS     SYS     SYS      X      PXB     PXB     PXB     SYS     32-63   1  N/A
GPU5    SYS     SYS     SYS     SYS     PXB      X      PXB     PXB     SYS     32-63   1  N/A
GPU6    SYS     SYS     SYS     SYS     PXB     PXB      X      PIX     SYS     32-63   1  N/A
GPU7    SYS     SYS     SYS     SYS     PXB     PXB     PIX      X      SYS     32-63   1  N/A
NIC0    NODE    NODE    NODE    NODE    SYS     SYS     SYS     SYS      X

Legend:

  X    = Self
  SYS  = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI)
  NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node
  PHB  = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU)
  PXB  = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge)
  PIX  = Connection traversing at most a single PCIe bridge
  NV#  = Connection traversing a bonded set of # NVLinks

NIC Legend:

  NIC0: ibp65s0

==============================
     Environment Variables
==============================
LD_LIBRARY_PATH=/root/.microsandbox/lib:/root/.local/lib:/root/.microsandbox/lib:/root/.local/lib:/usr/local/cuda/lib64:
MKL_THREADING_LAYER=GNU
MKL_SERVICE_FORCE_INTEL=1
CUDA_HOME=/usr/local/cuda-12.9
CUDA_HOME=/usr/local/cuda-12.9
PYTORCH_NVML_BASED_CUDA_CHECK=1
TORCHINDUCTOR_COMPILE_THREADS=1
TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_root

</details>

🐛 Describe the bug

Bug

The /v1/audio/transcriptions endpoint returns {"error": "Invalid or unsupported audio file."} for valid audio files when soundfile is not installed.

Root cause

soundfile is only in requirements/test.in, not in requirements/common.txt. A normal uv pip install -e . won't install it.
When soundfile is missing, it becomes a PlaceholderModule. The except soundfile.LibsndfileError in load_audio() (vllm/multimodal/media/audio.py:142) then raises an ImportError when evaluating the exception type. This ImportError is not caught by the except clause and bubbles up to speech_to_text.py:200, where it gets caught by a generic except Exception and replaced with the misleading "Invalid or unsupported audio file." message.

Proposed fix

Add soundfile to requirements/common.txt
Handle ImportError explicitly in load_audio() so a missing soundfile either falls through to pyav or raises a clear message like "Audio loading requires 'soundfile' or 'av' package. Install with: pip install soundfile"

Before submitting a new issue...

Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

extent analysis

TL;DR

Add soundfile to requirements/common.txt to ensure it's installed for audio file processing.

Guidance

Verify that soundfile is not installed by checking the output of pip list soundfile or attempting to import it in a Python environment.
Add soundfile to requirements/common.txt to include it in the installation process.
Consider handling ImportError explicitly in load_audio() to provide a clear error message when soundfile is missing.
Test the /v1/audio/transcriptions endpoint with a valid audio file after installing soundfile to confirm the fix.

Example

No code example is provided as the fix involves modifying the requirements/common.txt file and potentially updating the load_audio() function to handle ImportError.

Notes

The proposed fix assumes that soundfile is a required dependency for audio file processing. If pyav is intended to be a fallback, additional error handling may be necessary to ensure seamless audio processing.

Recommendation

Apply the workaround by adding soundfile to requirements/common.txt to ensure it's installed and available for audio file processing. This should resolve the "Invalid or unsupported audio file" error for valid audio files.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #API rate limit #retriever error #indexing error #environment variable

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

vllm - ✅(Solved) Fix [Bug]: Missing `soundfile` dependency breaks audio transcription [1 pull requests, 1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Fix / Workaround

============================== CPU Info

PR fix notes

PR #39473: fix: handle ImportError in load_audio

Description (problem / solution / changelog)

Summary

Root Cause

Changes

requirements/common.txt

vllm/multimodal/media/audio.py

Edge Cases

Changed files

Code Example

Your current environment

🐛 Describe the bug

Bug

Root cause

Proposed fix

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING

`requirements/common.txt`

`vllm/multimodal/media/audio.py`