langgenius/dify · warning · SpeechToTextDisabledError

speech_to_text_disabled

speech_to_text_disabled

Error message

Speech to text is disabled.

What it means

HTTP 400 with error_code `speech_to_text_disabled`, raised by SpeechToTextDisabledError when AudioService raises SpeechToTextDisabledServiceError. The app's speech-to-text feature flag is off in the model config, so the controller refuses the upload before any provider work. This is a configuration gate analogous to the suggested-questions disabled error.

Source

Thrown at api/controllers/console/explore/trial.py:692

                file=file,
                session=db.session(),
                end_user=None,
            )
            RecommendedAppService.add_trial_app_record(app_id, user_id, session=db.session())
            return response
        except services.errors.app_model_config.AppModelConfigBrokenError:
            logger.exception("App model config broken.")
            raise AppUnavailableError()
        except NoAudioUploadedServiceError:
            raise NoAudioUploadedError()
        except AudioTooLargeServiceError as e:
            raise AudioTooLargeError(str(e))
        except UnsupportedAudioTypeServiceError:
            raise UnsupportedAudioTypeError()
        except ProviderNotSupportSpeechToTextServiceError:
            raise ProviderNotSupportSpeechToTextError()
        except SpeechToTextDisabledServiceError:
            raise SpeechToTextDisabledError()
        except ProviderTokenNotInitError as ex:
            raise ProviderNotInitializeError(ex.description)
        except QuotaExceededError:
            raise ProviderQuotaExceededError()
        except ModelCurrentlyNotSupportError:
            raise ProviderModelCurrentlyNotSupportError()
        except InvokeError as e:
            raise CompletionRequestError(e.description)
        except ValueError as e:
            raise e
        except Exception as e:
            logger.exception("internal server error.")
            raise InternalServerError()


class TrialChatTextApi(TrialAppResource):
    @console_ns.expect(console_ns.models[TextToSpeechRequest.__name__])
    @console_ns.response(200, "Success", console_ns.models[AudioBinaryResponse.__name__])

View on GitHub (pinned to ef8544b173)

Solutions

1. Enable speech-to-text in the app studio (App Settings -> Speech to text), then publish.
2. Hide the audio upload control in the client when the app config reports STT disabled.
3. Do not retry - deterministic until the app config changes.

Example fix

// before - always show mic
<MicButton onSubmit={uploadAudio} />

// after - gate on app config
{app.speech_to_text?.enabled && <MicButton onSubmit={uploadAudio} />}

const app = await fetch(`/console/api/explore/apps/${appId}`).then(r => r.json())
if (!app.model_config?.speech_to_text?.enabled) {
  // do not show the mic / do not POST audio
}

function isSpeechToTextEnabled(app: any): boolean {
  return Boolean(app?.model_config?.speech_to_text?.enabled)
}

try {
  const r = await fetch(audioUrl, { method: 'POST', body: fd })
  if (r.status === 400) {
    const body = await r.json()
    if (body.code === 'speech_to_text_disabled') hideMicControl()
  }
} catch (e) { reportToUser(e) }

When it happens

Trigger: POST TrialChatAudioApi for an app whose `speech_to_text.enabled` config is false or absent, but the client still sends an audio file.

Common situations: UI shows a microphone button for an app that has STT disabled; app cloned from a template with STT off; operator disabled STT to save cost but the client was not updated.

Related errors

• provider_not_support_speech_to_text
• app_suggested_questions_after_answer_disabled
• no_audio_uploaded
• audio_too_large
• unsupported_audio_type

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/d7f08ce15c7a6c07. Report an issue: GitHub.