GigaChat Audio
PulseAugur coverage of GigaChat Audio — every cluster mentioning GigaChat Audio across labs, papers, and developer communities, ranked by signal.
- 2026-08-01 product_launch Sber updated GigaChat Audio to handle longer audio recordings and added new features for speaker separation and fact retention. source
- 2026-07-19 product_launch Sber updated its GigaChat Audio model and released an open-source version, GigaChat3.1-Audio-10B, along with the GigaAM Multilingual speech recognition family. source
- 2026-07-11 research_milestone Researchers released GigaChat Audio, a time-aware large audio language model capable of processing up to two hours of audio. source
-
Sber's GigaChat Audio now handles 3-hour recordings, adds speaker separation
Sber has updated its GigaChat Audio service, enhancing its ability to process up to three hours of audio. The updated version can now distinguish between speakers, generate summaries with timestamps, identify emotional …
-
Sber releases open-source GigaChat Audio with emotion detection and timestamping
Sber has updated its GigaChat Audio model, enhancing its ability to process audio files directly without full transcription and to detect emotional tones in speech. The updated model can now identify speakers, summarize…
-
New research tackles audio-language model limitations in instruction following and evaluation
Researchers are developing new methods to improve the capabilities of large audio-language models (LALMs). One approach focuses on using audio-aware LLMs to provide fine-grained feedback for better instruction following…
-
GigaChat Audio 10B model offers time-aware understanding for 2-hour audio
Researchers have developed GigaChat Audio, a novel time-aware large audio language model capable of understanding and answering questions about audio recordings up to two hours long. This model addresses the challenge o…