ModelEngine-Group / ModelEngine-Group/nexent
[Improvement] When invoking the TTS model, passing in the raw Markdown response causes the model to read out numerous special characters.
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 5.9k
- Forks
- 731
- Avg merge
- 19h 34m
- Merged PRs (30d)
- 172
Description
Improvement Description
调用tts模型时，传入是回答的原始markdown，导致模型会朗读很多特殊符号。
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at the TTS model invocation path in the repository and trace how the assistant's raw Markdown response is passed to speech synthesis. Identify the appropriate text form for TTS and verify that headings, formatting markers, and other Markdown symbols are not read aloud.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100