Skip to content

feat(assemblyai): add vad_threshold parameter for U3 Pro#3927

Merged
markbackman merged 2 commits intopipecat-ai:mainfrom
zkleb-aai:add-assemblyai-vad-threshold
Mar 5, 2026
Merged

feat(assemblyai): add vad_threshold parameter for U3 Pro#3927
markbackman merged 2 commits intopipecat-ai:mainfrom
zkleb-aai:add-assemblyai-vad-threshold

Conversation

@zkleb-aai
Copy link
Copy Markdown
Contributor

Add vad_threshold parameter to AssemblyAIConnectionParams to support voice activity detection threshold configuration for the u3-rt-pro model.

This parameter allows users to align AssemblyAI's VAD threshold with their external VAD systems (e.g., Silero VAD) to avoid the "dead zone" where AssemblyAI transcribes speech that the external VAD hasn't detected yet, which can delay interruption handling.

  • Range: 0.0 to 1.0 (lower = more sensitive)
  • Default: 0.3 (API default when not sent)
  • Only applicable to u3-rt-pro model
  • Automatically included in WebSocket query parameters

Recommended usage: Set vad_threshold to match your VAD's activation threshold (e.g., both at 0.3) for optimal performance.

Please describe the changes in your PR. If it is addressing an issue, please reference that as well.

@codecov
Copy link
Copy Markdown

codecov Bot commented Mar 5, 2026

Codecov Report

❌ Patch coverage is 0% with 1 line in your changes missing coverage. Please review.

Files with missing lines Patch % Lines
src/pipecat/services/assemblyai/models.py 0.00% 1 Missing ⚠️
Files with missing lines Coverage Δ
src/pipecat/services/assemblyai/models.py 0.00% <0.00%> (ø)
🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

@zkleb-aai zkleb-aai force-pushed the add-assemblyai-vad-threshold branch from 5df3d6b to 7ecb75e Compare March 5, 2026 20:09
zkleb-aai added a commit to zkleb-aai/docs that referenced this pull request Mar 5, 2026
Add documentation for the vad_threshold parameter in AssemblyAI U3 Pro:

- Add vad_threshold to AssemblyAIConnectionParams table
- Add usage example showing VAD threshold alignment with Silero VAD
- Add note about VAD threshold alignment to avoid "dead zone"
- Explain the misalignment issue between AssemblyAI (default 0.3) and
  Pipecat's Silero VAD (default 0.7)

This corresponds to the vad_threshold parameter added in pipecat-ai/pipecat#3927
Copy link
Copy Markdown
Contributor

@markbackman markbackman left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add vad_threshold parameter to AssemblyAIConnectionParams to support
voice activity detection threshold configuration for the u3-rt-pro model.

This parameter allows users to align AssemblyAI's VAD threshold with
their external VAD systems (e.g., Silero VAD) to avoid the "dead zone"
where AssemblyAI transcribes speech that the external VAD hasn't
detected yet, which can delay interruption handling.

- Range: 0.0 to 1.0 (lower = more sensitive)
- Default: 0.3 (API default when not sent)
- Only applicable to u3-rt-pro model
- Automatically included in WebSocket query parameters

Recommended usage: Set vad_threshold to match your VAD's activation
threshold (e.g., both at 0.3) for optimal performance.
@zkleb-aai zkleb-aai force-pushed the add-assemblyai-vad-threshold branch from 7ecb75e to acfb07f Compare March 5, 2026 20:27
zkleb-aai added a commit to zkleb-aai/docs that referenced this pull request Mar 5, 2026
- Add vad_threshold parameter documentation for U3 Pro
- Remove formatted_finals (v2 API legacy parameter)
- Remove word_finalization_max_wait_time (v2 API legacy parameter)
- Clarify format_turns only applies to Universal-Streaming models
- Add VAD threshold alignment usage example and notes

This corresponds to the code changes in pipecat-ai/pipecat#3927
@markbackman markbackman merged commit f4dfeb0 into pipecat-ai:main Mar 5, 2026
6 checks passed
zkleb-aai added a commit to zkleb-aai/docs that referenced this pull request Mar 5, 2026
- Add vad_threshold parameter documentation for U3 Pro
- Remove formatted_finals (v2 API legacy parameter)
- Remove word_finalization_max_wait_time (v2 API legacy parameter)
- Clarify format_turns only applies to Universal-Streaming models
- Add VAD threshold alignment usage example and notes

This corresponds to the code changes in pipecat-ai/pipecat#3927
zkleb-aai added a commit to zkleb-aai/docs that referenced this pull request Mar 5, 2026
- Add vad_threshold parameter documentation for U3 Pro
- Remove formatted_finals (v2 API legacy parameter)
- Remove word_finalization_max_wait_time (v2 API legacy parameter)
- Clarify format_turns only applies to Universal-Streaming models
- Add VAD threshold alignment usage example and notes

This corresponds to the code changes in pipecat-ai/pipecat#3927
zkleb-aai added a commit to zkleb-aai/docs that referenced this pull request Mar 5, 2026
- Add vad_threshold parameter documentation for U3 Pro
- Remove formatted_finals (v2 API legacy parameter)
- Remove word_finalization_max_wait_time (v2 API legacy parameter)
- Clarify format_turns only applies to Universal-Streaming models
- Add VAD threshold alignment usage example and notes

This corresponds to the code changes in pipecat-ai/pipecat#3927
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants