Skip to content

more vad_analyzer fixes #522

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
aconchillo merged 1 commit into from
Feb 1, 2026
Merged

more vad_analyzer fixes #522

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 3 additions & 6 deletions guides/learn/speech-input.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,9 +57,7 @@ vad_analyzer = SileroVADAnalyzer(

user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
),
user_params=LLMUserAggregatorParams(vad_analyzer=vad_analyzer)),
)
```

Expand Down Expand Up @@ -190,9 +188,7 @@ vad_params = VADParams(
)

transport = YourTransport(
params=TransportParams(
vad_analyzer=SileroVADAnalyzer(params=vad_params),
),
params=TransportParams(),
)

# Configure Smart Turn via user turn strategies (if using turn detection)
Expand All @@ -204,6 +200,7 @@ user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
turn_analyzer=LocalSmartTurnAnalyzerV3()
)]
) if using_smart_turn_detection else None,
vad_analyzer=SileroVADAnalyzer(params=vad_params),
),
)

Expand Down
24 changes: 22 additions & 2 deletions server/utilities/audio/aic-filter.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,10 +28,10 @@ pip install "pipecat-ai[aic]"
</ParamField>

<ParamField path="model_id" type="Optional[str]" default="None">
Model identifier to download from CDN. Required if `model_path` is not provided.
Model identifier to download from CDN. Required if `model_path` is not provided.
See [artifacts.ai-coustics.io](https://artifacts.ai-coustics.io/) for available models.
See the [documentation](https://docs.ai-coustics.com/guides/models) for more detailed information about the models.

Examples: `"quail-vf-l-16khz"`, `"quail-s-16khz"`, `"quail-l-8khz"`
</ParamField>

Expand Down Expand Up @@ -110,6 +110,10 @@ The recommended approach is to use `AICFilter` with its built-in VAD analyzer:

```python
from pipecat.audio.filters.aic_filter import AICFilter
from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.transports.services.daily import DailyTransport, DailyParams

# Create the AIC filter
Expand All @@ -127,6 +131,12 @@ transport = DailyTransport(
audio_in_enabled=True,
audio_out_enabled=True,
audio_in_filter=aic_filter,
),
)

user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(
vad_analyzer=aic_filter.create_vad_analyzer(
speech_hold_duration=0.05,
minimum_speech_duration=0.0,
Expand Down Expand Up @@ -169,6 +179,10 @@ The AIC filter works with any Pipecat transport:

```python
from pipecat.audio.filters.aic_filter import AICFilter
from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.transports.websocket import FastAPIWebsocketTransport, FastAPIWebsocketParams

aic_filter = AICFilter(
Expand All @@ -181,6 +195,12 @@ transport = FastAPIWebsocketTransport(
audio_in_enabled=True,
audio_out_enabled=True,
audio_in_filter=aic_filter,
),
)

user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(
vad_analyzer=aic_filter.create_vad_analyzer(
speech_hold_duration=0.05,
sensitivity=6.0,
Expand Down