diff --git a/enterprise/app/services/messages/audio_transcription_service.rb b/enterprise/app/services/messages/audio_transcription_service.rb
index 0e574cb03..c502b717a 100644
--- a/enterprise/app/services/messages/audio_transcription_service.rb
+++ b/enterprise/app/services/messages/audio_transcription_service.rb
@@ -2,6 +2,10 @@ class Messages::AudioTranscriptionService< Llm::LegacyBaseOpenAiService
   include Integrations::LlmInstrumentation
 
   WHISPER_MODEL = 'whisper-1'.freeze
+  # Whisper's hard limit is 25 MB *decimal* (25_000_000), not binary (25.megabytes
+  # = 26_214_400) — using the binary form leaks the 25.0–26.2 MB range to the API
+  # as 413s. Long audio (~70+ min Opus) keeps the attachment but skips transcription.
+  WHISPER_BYTE_LIMIT = 25_000_000
 
   attr_reader :attachment, :message, :account
 
@@ -15,6 +19,7 @@ class Messages::AudioTranscriptionService< Llm::LegacyBaseOpenAiService
   def perform
     return { error: 'Transcription limit exceeded' } unless can_transcribe?
     return { error: 'Message not found' } if message.blank?
+    return { error: 'Audio too large for Whisper' } if audio_too_large?
 
     transcriptions = transcribe_audio
     Rails.logger.info "Audio transcription successful: #{transcriptions}"
@@ -33,6 +38,13 @@ class Messages::AudioTranscriptionService< Llm::LegacyBaseOpenAiService
     account.usage_limits[:captain][:responses][:current_available].positive?
   end
 
+  def audio_too_large?
+    blob = attachment.file&.blob
+    return false unless blob
+
+    blob.byte_size > WHISPER_BYTE_LIMIT
+  end
+
   def fetch_audio_file
     blob = attachment.file.blob
     temp_dir = Rails.root.join('tmp/uploads/audio-transcriptions')
@@ -63,11 +75,14 @@ class Messages::AudioTranscriptionService< Llm::LegacyBaseOpenAiService
     transcribed_text = nil
 
     File.open(temp_file_path, 'rb') do |file|
+      # temperature: 0.0 minimises Whisper's hallucinations on silence /
+      # near-silent audio; non-zero values trigger spiraling repeats like
+      # "Oh, dear. Oh, dear. Oh, dear." — well-documented Whisper behaviour.
       response = @client.audio.transcribe(
         parameters: {
           model: WHISPER_MODEL,
           file: file,
-          temperature: 0.4
+          temperature: 0.0
         }
       )
       transcribed_text = response['text']
diff --git a/spec/enterprise/services/messages/audio_transcription_service_spec.rb b/spec/enterprise/services/messages/audio_transcription_service_spec.rb
index 7ece2540a..212c0bf01 100644
--- a/spec/enterprise/services/messages/audio_transcription_service_spec.rb
+++ b/spec/enterprise/services/messages/audio_transcription_service_spec.rb
@@ -63,6 +63,23 @@ RSpec.describe Messages::AudioTranscriptionService, type: :service do
         expect(result).to eq({ success: true, transcriptions: 'Existing transcription' })
       end
     end
+
+    context 'when the audio exceeds Whisper byte limit' do
+      before do
+        attachment.file.attach(
+          io: File.open(Rails.public_path.join('audio/widget/ding.mp3')),
+          filename: 'large.mp3',
+          content_type: 'audio/mpeg'
+        )
+        allow(service).to receive(:can_transcribe?).and_return(true)
+        allow(attachment.file.blob).to receive(:byte_size).and_return(described_class::WHISPER_BYTE_LIMIT + 1)
+      end
+
+      it 'returns an error without calling Whisper' do
+        expect(service).not_to receive(:transcribe_audio)
+        expect(service.perform).to eq({ error: 'Audio too large for Whisper' })
+      end
+    end
   end
 
   describe '#fetch_audio_file' do