langgenius/dify · error · SpeechToTextDisabledError

speech_to_text_disabled

speech_to_text_disabled

Error message

Speech to text is disabled.

What it means

Raised by _transcribe_audio_to_text when AudioService raises SpeechToTextDisabledServiceError — the speech-to-text feature is disabled in the system/tenant configuration. Translated to SpeechToTextDisabledError (400, error_code 'speech_to_text_disabled').

Source

Thrown at api/controllers/console/app/audio.py:163

                agent_soul=agent_soul,
                file=file,
                session=session,
                end_user=None,
            )
        return dump_response(AudioTranscriptResponse, 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 HTTPException:
        raise
    except ValueError:
        raise
    except Exception as e:
        logger.exception("Failed to transcribe audio to text")
        raise InternalServerError() from e


@console_ns.route("/apps/<uuid:app_id>/audio-to-text")

View on GitHub (pinned to ef8544b173)

Solutions

1. Enable speech-to-text in the system/tenant configuration (set the relevant SPEECH_TO_TEXT config flag).
2. Restart the API service after changing the config.
3. Confirm the feature is enabled in the admin console before users hit the endpoint.
4. Hide the audio upload UI when STT is disabled.

Example fix

# before: .env
SPEECH_TO_TEXT_ENABLED=false

# after
SPEECH_TO_TEXT_ENABLED=true

try { await axios.post(`/apps/${id}/audio-to-text`, form); }
catch (e) { if (e.code === 'speech_to_text_disabled') { /* hide audio UI; surface to admin */ } }

When it happens

Trigger: Calling the audio-to-text endpoint when the STT feature flag is off at the system or tenant level, regardless of provider configuration.

Common situations: Self-hosted deployment where SPEECH_TO_TEXT is disabled by default; admin disabled the feature; tenant settings override turned STT off.

Related errors

• provider_not_support_speech_to_text
• app_unavailable
• no_audio_uploaded
• unsupported_audio_type
• provider_quota_exceeded

AI-assisted analysis of langgenius/dify@ef8544b173 (2026-08-12). Data as JSON: /api/errors/89c11fb3d73bc24f. Report an issue: GitHub.