inworld/sava

voice-activity-detection model by inworld

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

SAVA Semantic acoustic voice activity: streaming speech and end-of-turn detection in one model with an open license. SAVA returns two probabilities for a live audio stream: The model's shared network uses acoustic and sentence context to distinguish speech from coughs, laughs, music and keyboard clatter. Use it to open a turn when speech starts and close it when the sentence is complete. The reference turn policy turns the probabilities into segments; applications can supply their own policy. SAVA responds to any voice. It does not pick out a target speaker, and it leaves interruptions and backchannels to the application's dialogue policy. Using a coding agent? Point it at the setup section of AGENTS.md: it installs the package, checks the machine with sava-doctor and runs SAVA on a first recording. With Python 3.10 or later: sava.load("inworld/sava") and the CLI's default model download the weights on first use and verify their checksum.…

inworld/sava on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-20T10:01:08.069Z

Inside the original model card — Document outline
  1. TL;DR
  2. Quick start
  3. Hardware
  4. The benchmarks
  5. Architecture
  6. Training data
  7. License
  8. How to contribute

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

inworld/sava is a voice-activity-detection model repository published by inworld on Hugging Face. The source reports the inworld-sava library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
voice-activity-detection
Library
inworld-sava
Recent downloads (30 days)
0
Cumulative likes
63
Hugging Face trending score
44
Reported safetensors parameters
Not reported
Architecture
Not reported
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-11-14T02:13:41.000Z
Last modified
2026-11-14T02:13:43.000Z

Compatibility and lineage

Language coverage was not reported.

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-20T07:00:14.581Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

pyannote/segmentation-3.0

nvidia/Nemotron-3-Diarization

telenow/telenow-pvad-v1