Add Deepgram Flux STT service for AWS SageMaker#4143
Merged
Conversation
Add DeepgramFluxSageMakerSTTService that combines SageMaker's HTTP/2 transport with Flux's JSON turn detection protocol (StartOfTurn, EndOfTurn, EagerEndOfTurn, TurnResumed). Includes mid-stream Configure support, silence watchdog, and an example bot.
Codecov Report❌ Patch coverage is
... and 44 files with indirect coverage changes 🚀 New features to boost your workflow:
|
filipi87
reviewed
Mar 26, 2026
filipi87
reviewed
Mar 26, 2026
| UserStartedSpeakingFrame, | ||
| UserStoppedSpeakingFrame, | ||
| ) | ||
| from pipecat.processors.frame_processor import FrameDirection |
filipi87
approved these changes
Mar 26, 2026
Contributor
filipi87
left a comment
filipi87
left a comment
There was a problem hiding this comment.
@chadbailey59 this works great.
As a suggestion, I have a follow-up PR where:
- We create a base class,
DeepgramFluxSTTBase, so we can reuse Deepgram Flux logic across both services. - We move
flux_stt.pytodeepgram/flux/sagemaker/stt.py.
Creating a base class, DeepgramFluxSTTBase, to reuse Deepgram Flux logic
Contributor
|
@filipi87 is this ready to be merged now? |
Contributor
Hi @markbackman, I think so. 👍 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I (well, Claude) basically combined the existing DeepgramSageMakerSTTService and DeepgramFluxService to make a DeepgramFluxSageMakerSTTService. I ran the included new example, and everything worked as it should. There weren't any existing automated tests for Deepgram Flux, and it's additionally impractical to run tests on these SageMaker services because of setup and teardown.
Summary
DeepgramFluxSageMakerSTTServicethat combines SageMaker's HTTP/2 bidirectional transport (SageMakerBidiClient) with Deepgram Flux's JSON turn detection protocolConfiguresupport for updatable fields (keyterm, eot_threshold, eager_eot_threshold, eot_timeout_ms)07c-interruptible-deepgram-flux-sagemaker.py) using Flux STT + SageMaker TTS + AWS Bedrock LLM withExternalUserTurnStrategiesTest plan
from pipecat.services.deepgram.sagemaker.flux_stt import DeepgramFluxSageMakerSTTServiceruff checkandruff format --checkuv run pytest tests/ -x)🤖 Generated with Claude Code