Support Minimax TTS #14480

Closed
opened 2026-02-21 19:17:26 -05:00 by yindo · 3 comments
Owner

Originally created by @LU-V on GitHub (Jun 7, 2025).

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

1.0.0 & 1.3.0

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

After turning on Minimax TTS, the chat cannot be carried out

Image

The page shows no sound

Image

Image

dify-api system error
Image

✔️ Expected Behavior

Supports Minimax models, such as speach-02-hd

Actual Behavior

No response

Originally created by @LU-V on GitHub (Jun 7, 2025). ### Self Checks - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [x] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue,否则会被关闭。谢谢!:) - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version 1.0.0 & 1.3.0 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce After turning on Minimax TTS, the chat cannot be carried out ![Image](https://github.com/user-attachments/assets/ffe87716-4a08-4885-9c0e-585f8cf16cba) The page shows no sound ![Image](https://github.com/user-attachments/assets/4b149ed7-4877-47c6-8d53-b6567da4fcaf) ![Image](https://github.com/user-attachments/assets/39a15c47-b731-4bf2-8062-3ef3f35cde05) dify-api system error ![Image](https://github.com/user-attachments/assets/348d7133-2497-4c87-bbf9-f2edee64c5d8) ### ✔️ Expected Behavior Supports Minimax models, such as speach-02-hd ### ❌ Actual Behavior _No response_
yindo added the stt & tts label 2026-02-21 19:17:26 -05:00
yindo closed this issue 2026-02-21 19:17:26 -05:00
Author
Owner

@dosubot[bot] commented on GitHub (Jun 7, 2025):

Hi @LU-V! I'm Dosu and I’m helping the dify team.

Dify does support Minimax as a TTS provider through its modular provider system, but enabling it requires a few key steps. Make sure the HOSTED_MINIMAX_ENABLED flag is set to true in your configuration, and that you have valid credentials for Minimax in your provider settings. Minimax must also be registered in the provider list, which it is by default in recent versions (source).

The error you’re seeing (IndexError: list index out of range) is likely due to a misconfiguration or missing/incorrect input mapping in your workflow, especially in how user inputs are mapped to the variable pool (source). Double-check that all required variables for TTS are present and correctly mapped.

A few troubleshooting tips:

  • Ensure your workflow is published; TTS features won’t activate until then.
  • If you’re using Firefox, try Chrome or Edge, as browser audio support can differ.
  • Make sure your Minimax TTS model outputs audio in a browser-compatible format (mp3 is safest).
  • If you’re still seeing the error, review your workflow’s input mapping and provider credentials for completeness.

If you need to check the provider setup, look at the HostedMinmaxConfig and init_minimax logic in the codebase (source, source). The TTS system is provider-agnostic, so once Minimax is enabled and configured, it should work like any other TTS provider.

Let me know if you need more details on any of these steps!

To reply, just mention @dosu.


How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Join Discord Share on X

@dosubot[bot] commented on GitHub (Jun 7, 2025): <!-- Greeting --> Hi @LU-V! I'm [Dosu](https://go.dosu.dev/dosubot) and I’m helping the dify team. <!-- Answer --> Dify does support Minimax as a TTS provider through its modular provider system, but enabling it requires a few key steps. Make sure the `HOSTED_MINIMAX_ENABLED` flag is set to `true` in your configuration, and that you have valid credentials for Minimax in your provider settings. Minimax must also be registered in the provider list, which it is by default in recent versions ([source](https://github.com/langgenius/dify/blob/65c7c01d90e5af44d4c9ff41689a855a7a82c772/api/core/model_runtime/model_providers/_position.yaml)). The error you’re seeing (`IndexError: list index out of range`) is likely due to a misconfiguration or missing/incorrect input mapping in your workflow, especially in how user inputs are mapped to the variable pool ([source](https://github.com/langgenius/dify/blob/65c7c01d90e5af44d4c9ff41689a855a7a82c772/api/core/workflow/workflow_entry.py)). Double-check that all required variables for TTS are present and correctly mapped. A few troubleshooting tips: - Ensure your workflow is published; TTS features won’t activate until then. - If you’re using Firefox, try Chrome or Edge, as browser audio support can differ. - Make sure your Minimax TTS model outputs audio in a browser-compatible format (mp3 is safest). - If you’re still seeing the error, review your workflow’s input mapping and provider credentials for completeness. If you need to check the provider setup, look at the `HostedMinmaxConfig` and `init_minimax` logic in the codebase ([source](https://github.com/langgenius/dify/blob/65c7c01d90e5af44d4c9ff41689a855a7a82c772/api/configs/feature/hosted_service/__init__.py), [source](https://github.com/langgenius/dify/blob/65c7c01d90e5af44d4c9ff41689a855a7a82c772/api/core/hosting_configuration.py)). The TTS system is provider-agnostic, so once Minimax is enabled and configured, it should work like any other TTS provider. Let me know if you need more details on any of these steps! <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=other)</sup>&nbsp;&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify/issues/20782)
Author
Owner

@LU-V commented on GitHub (Jun 7, 2025):

Hi @LU-V! I'm Dosu and I’m helping the dify team.

Dify does support Minimax as a TTS provider through its modular provider system, but enabling it requires a few key steps. Make sure the HOSTED_MINIMAX_ENABLED flag is set to true in your configuration, and that you have valid credentials for Minimax in your provider settings. Minimax must also be registered in the provider list, which it is by default in recent versions (source).

The error you’re seeing (IndexError: list index out of range) is likely due to a misconfiguration or missing/incorrect input mapping in your workflow, especially in how user inputs are mapped to the variable pool (source). Double-check that all required variables for TTS are present and correctly mapped.

A few troubleshooting tips:

  • Ensure your workflow is published; TTS features won’t activate until then.
  • If you’re using Firefox, try Chrome or Edge, as browser audio support can differ.
  • Make sure your Minimax TTS model outputs audio in a browser-compatible format (mp3 is safest).
  • If you’re still seeing the error, review your workflow’s input mapping and provider credentials for completeness.

If you need to check the provider setup, look at the HostedMinmaxConfig and init_minimax logic in the codebase (source, source). The TTS system is provider-agnostic, so once Minimax is enabled and configured, it should work like any other TTS provider.

Let me know if you need more details on any of these steps!

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Join Discord Share on X

After reconfiguring, I found that the TTS model of minimax is supported, but voice cannot be selected

@LU-V commented on GitHub (Jun 7, 2025): > Hi [@LU-V](https://github.com/LU-V)! I'm [Dosu](https://go.dosu.dev/dosubot) and I’m helping the dify team. > > Dify does support Minimax as a TTS provider through its modular provider system, but enabling it requires a few key steps. Make sure the `HOSTED_MINIMAX_ENABLED` flag is set to `true` in your configuration, and that you have valid credentials for Minimax in your provider settings. Minimax must also be registered in the provider list, which it is by default in recent versions ([source](https://github.com/langgenius/dify/blob/65c7c01d90e5af44d4c9ff41689a855a7a82c772/api/core/model_runtime/model_providers/_position.yaml)). > > The error you’re seeing (`IndexError: list index out of range`) is likely due to a misconfiguration or missing/incorrect input mapping in your workflow, especially in how user inputs are mapped to the variable pool ([source](https://github.com/langgenius/dify/blob/65c7c01d90e5af44d4c9ff41689a855a7a82c772/api/core/workflow/workflow_entry.py)). Double-check that all required variables for TTS are present and correctly mapped. > > A few troubleshooting tips: > > * Ensure your workflow is published; TTS features won’t activate until then. > * If you’re using Firefox, try Chrome or Edge, as browser audio support can differ. > * Make sure your Minimax TTS model outputs audio in a browser-compatible format (mp3 is safest). > * If you’re still seeing the error, review your workflow’s input mapping and provider credentials for completeness. > > If you need to check the provider setup, look at the `HostedMinmaxConfig` and `init_minimax` logic in the codebase ([source](https://github.com/langgenius/dify/blob/65c7c01d90e5af44d4c9ff41689a855a7a82c772/api/configs/feature/hosted_service/__init__.py), [source](https://github.com/langgenius/dify/blob/65c7c01d90e5af44d4c9ff41689a855a7a82c772/api/core/hosting_configuration.py)). The TTS system is provider-agnostic, so once Minimax is enabled and configured, it should work like any other TTS provider. > > Let me know if you need more details on any of these steps! > > _To reply, just mention [@dosu](https://go.dosu.dev/dosubot)._ > > How did I do? [Good](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/e06a7c7e-0471-49b5-9901-261050b4842d?feedback_type=other)  [![Join Discord](https://camo.githubusercontent.com/d562c2df5e4567ea41d37f1d91a4da0839d8341037045b103b2da268998de17f/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f6a6f696e2d3538363546323f6c6f676f3d646973636f7264266c6f676f436f6c6f723d7768697465266c6162656c3d)](https://go.dosu.dev/discord-bot) [![Share on X](https://camo.githubusercontent.com/4649f705e2396d6f328dbc8e800a0509c9c17b3b20253b36706c393df124b93d/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f582d73686172652d626c61636b)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify/issues/20782) After reconfiguring, I found that the TTS model of minimax is supported, but voice cannot be selected
Author
Owner

@crazywoola commented on GitHub (Jun 8, 2025):

Duplicated https://github.com/langgenius/dify-official-plugins/issues/476

@crazywoola commented on GitHub (Jun 8, 2025): Duplicated https://github.com/langgenius/dify-official-plugins/issues/476
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#14480