QuantumNous / QuantumNous/new-api
/v1/audio/transcriptions接口不支持流式请求
Open
Nobody has claimed this yet.
bug
- Dominant language
- Go
- Stars
- 48.5k
- Forks
- 11.6k
- Avg merge
- 1d 17h
- Merged PRs (30d)
- 58
Description
提交前必读(请勿删除本节)
- 文档:https://docs.newapi.ai/
- 使用问题先看或先问:https://deepwiki.com/QuantumNous/new-api
- 开启透传后的转发相关反馈不接受 issue;透传模式会直接转发请求,请自行确认上游行为。
- 不接受 coding plan、逆向渠道等技术支持类 issue。
- 警告:删除本模板、删除小节标题或随意清空内容的 issue,可能会被直接关闭;重复恶意提交者可能会被 block。
您当前的 newapi 版本
v1.0.0-rc6
提交确认
- 非重复 issue: 我已搜索现有 Issues,确认目前没有类似 issue。
- 提交前必读: 我已完整阅读上方“提交前必读”,并已查看文档 https://docs.newapi.ai/、项目 README 且向 AI 提问,确认这不是使用、配置或接入类问题。
- 模板完整: 我未删除此模板中的任何引导内容或小节标题,并会按要求完整填写。
- 维护成本: 我理解项目维护者精力有限,不遵循模板要求的 issue 可能会被无视或直接关闭。
问题描述
/v1/audio/transcriptions接口不支持流式响应
复现步骤
curl -N https://<newapi域名>/v1/audio/transcriptions \
-H 'Authorization: Bearer sk-apikey' \
-F model=qwen3-asr-1.7b \
-F file=@speech.wav \
-F stream=true
预期结果
正常应该流式返回大模型的响应,但是实际newapi等待上游响应完毕后一次性返回了所有的流式响应。
相关截图
Contributor guide
No contributing guide indexed for this repository
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 by tracing the handler and upstream response path for /v1/audio/transcriptions, focusing on how the stream=true request is forwarded and returned. Reproduce the issue with the provided curl -N command, then verify that response data reaches the client incrementally instead of arriving only after the upstream request completes.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- go
- Domain
- api, backend
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 48/100