TEN-framework / TEN-framework/ten-framework

How to use Gemini live API in China?

Open
#1,010 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
11.1k
Forks
1.4k
Avg merge
2d 15m
Merged PRs (30d)
22

Description

In the voice_assistant_realime graph, I've tested the Stepfun realtime api and it works fine.
I also tested voice_assistant with Gemini LLM (gemini-2.0-flash) which also works fine.
But the gemini-2.0-flash-live-001 doesn't work in voice_assistant_realime graph` (no output at all), and I didn't see any error in browser's console or docker's "task run".

How to diagnose where's the problem?
PS. I'm in China, but the network should be fine since a proxy is used and gemini-2.0-flash works fine.

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

Start with the voice_assistant_realime graph and compare its behavior with the working voice_assistant graph using gemini-2.0-flash. Trace the gemini-2.0-flash-live-001 request and check browser console and Docker task-run output; done means identifying why the live graph produces no output and documenting a reproducible diagnostic path.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, audio-video-rtc
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.