spring-projects / spring-projects/spring-ai
Support for Gemini transcript models
Nobody has claimed this yet.
- 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
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 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