OpenMOSS / OpenMOSS/MOSS-TTS

API Service Without Guardrails?

Open
#201 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.1k
Forks
373
Avg merge
20m
Merged PRs (30d)
1

Description

Hello,

Sorry if this is not the right place to ask — I also tried reaching out via WeChat customer service, but couldn’t get a helpful answer.

I noticed that the official API service is deployed with guardrails. During TTS usage, some of the input text I send gets blocked, and in several cases I believe these are false positives.

I’m wondering:

Do you provide an API service without guardrails (or with configurable guardrails)?
If not, are there recommended ways to handle or reduce false positives in the current setup?

Any guidance would be appreciated. Thanks!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no files, tests, or entry points. First confirm whether the official API's guardrails are configurable and whether false-positive handling is documented; done means a maintainer answers the availability and mitigation questions.

Written by the indexing model from the issue text.

Assessment

Domain
api, security
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.