The error "stt is not enabled" keeps appearing when using the voice input function

[equipaidFor218]

Self Checks

• This is only for bug report, if you would like to ask a question, please head to Discussions.
• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

Dify version

the latest(online dify);v0.10.0(local dify(source))

Cloud or Self Hosted

Cloud, Self Hosted (Source)

Steps to reproduce

✔️ Expected Behavior

When using dify locally, I called SiliconFlow's voice model FunAudioLLM/SenseVoiceSmall to enable my agent to have voice input functionality. In fact, before using voice input, all steps were fine. Then I used the online dify to build a simple agent and utilized the same model, hoping to perform voice input.

❌ Actual Behavior

In both cases, the error "stt is not enabled" appears

[dosubot]

Hello @equipaidFor218! I'm here to help you with bug reports, answer questions, and guide you on becoming a contributor. Let's tackle this issue together!

To resolve the "stt is not enabled" error when using the voice input function with SiliconFlow's voice model FunAudioLLM/SenseVoiceSmall in both local and online Dify environments, you should:

1. Ensure that the speech-to-text feature is enabled in the settings.
2. Save or publish your changes after enabling the voice input feature.
3. Start a new conversation, as the feature will not work in existing conversations until these steps are completed.

Additionally, if you are using Dify v0.13.1 (self-hosted via Docker), be aware of a known bug causing a Bad Request Error (400) related to JSON parsing issues. The Dify team is working on a fix, and this error may persist until a future update is released ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[equipaidFor218]

I'm sure that the stt fearture is enabled in the setting. Obivously ,if the feature is not enabled ,the “voice input” button would not appear，and There are no other errors except "stt isn not enabled".In addition, I hereby confirm that the Settings screen you mentioned is under the "Function" button of the workflow. If so, my understanding should be correct. Please confirm other possible problems。

[dosubot]

After enabling the speech-to-text feature in the settings, make sure to publish the app. This step is crucial because the feature needs to be published to become active. Once published, start a new conversation, as the feature will not work in existing conversations until these steps are completed. This is a known issue that the Dify team is working to fix ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}

[equipaidFor218]

Got it! TKU Dosu! And there is an another question for my local dify,which use the http protocol. So it will show an error message saying "microphone not authorized", and I want to know what the solution is.