spring-projects / spring-projects/spring-ai

Support for Gemini transcript models

Open
#6,812 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

status: waiting-for-triage
Dominant language
Java
Stars
9.5k
Forks
2.9k
Avg merge
1d 7h
Merged PRs (30d)
6

Description

Expected Behavior

Support for Chirp 2 / Chirp 3 transcription models, and globally, support for Google GenAI transcript models
Also support for micrometer metrics associated with transcription

Current Behavior

Only OpenAi transcription is supported, with no micrometer metrics associated with transcription

Context

We would like to qualify Chirp 2 and 3 in our existing infrastructure for speech to text
Multimodal completions with other Gemini models (e.g. gemini-2.5-flash) can be workaround in the meantime

Contributor guide

Open the contributing guide

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 by tracing the existing OpenAI transcription support in the repository and how transcription metrics are currently handled. Define completion as support for Chirp 2 and Chirp 3, broader Google GenAI transcript models, and associated micrometer metrics; use the existing multimodal completion workaround as context.

Written by the indexing model from the issue text.

Assessment

Tech stack
google-cloud, java
Domain
ai, backend
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
58/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.