Published 15 September 2026
Gemini 3.8 Audio (Live, Live Extended Thinking, Flash TTS, Flash-Lite TTS)
Model Cards are intended to provide essential information on Gemini models, including known limitations, mitigation approaches, and safety performance. Model cards may be updated from time to time; for example, to include updated evaluations as the model is improved or revised. See the Google DeepMind site for a comprehensive list of model cards.
Published: September 2026
Model Information
Description
Gemini 3.8 Audio (Live, Live Extended Thinking, Flash TTS, Flash-Lite TTS) is an addition to the Gemini 3 series of highly-capable models. This model card describes the native capabilities (e.g., image and audio) as additional outputs of Gemini. Information specific to these modalities is specified in-line and referred to as Gemini 3.8 Live, Gemini 3.8 Live Extended Thinking, Gemini 3.8 Flash TTS, and Gemini 3.8 Flash-Lite TTS (collectively as Gemini 3.8 Audio).
Model dependencies
Gemini 3.8 Audio is based on Gemini 3 Pro.
Inputs
Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking: Audio, images, video, and text with a token context window of up to 128K.
Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS: Text up to 8K.
Outputs
Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking: Audio and text, with 64K token output.
Gemini 3.8 Flash TTS and 3.8 Flash-Lite TTS: Audio, with 64K token output.
Architecture
Gemini 3.8 Audio models are based on Gemini 3 Pro. For more information about the model architecture, see the Gemini 3 Pro model card.
Model Data
Training Dataset
Gemini 3.8 Audio models are based on Gemini 3 Pro. For more information about the training dataset, see the Gemini 3 Pro model card.
Training Data Processing
For more information about the training data processing for Gemini 3.8 Audio models, see the Gemini 3 Pro model card.
Implementation and Sustainability
Hardware
Gemini 3.8 Audio models are based on Gemini 3 Pro. For more information about the hardware for Gemini 3 Pro and our continued commitment to operate sustainably, see the Gemini 3 Pro model card.
Software
Gemini 3.8 Audio models are based on Gemini 3 Pro. For more information about the software for Gemini 3 Pro, see the Gemini 3 Pro model card.
Distribution
Gemini 3.8 Audio is distributed in the following channels; respective documentation shared in line:
Gemini 3.8 Live
Gemini 3.8 Live Extended Thinking
- Gemini App
- Gemini API
- Google AI Studio
- Gemini Enterprise Agent Platform
- Google Workspace (Gmail, Docs, and Keep)
Gemini 3.8 Flash TTS
Gemini 3.8 Flash-Lite TTS
Our models are available to downstream providers via an application program interface (API) and subject to relevant terms of use. There is no required hardware or software to use the model. For AI Studio and Gemini API, see the Gemini API Additional Terms of Service; for Gemini Enterprise Agent Platform, see Google Cloud Platform Terms of Service. For more information, see Gemini Model API instructions and Gemini API quickstart.
Evaluation
Approach
Gemini 3.8 Audio models were evaluated across a range of benchmarks. For more details, see:
Intended Usage and Limitations
Benefit and Intended Usage
Gemini 3.8 Audio models process continuous streams of audio, video, and text to deliver spoken responses in real-time to create natural conversational experiences well-suited for users, developers, and enterprises.
Known Limitations
Gemini 3.8 Audio may exhibit some of the general limitations of foundation models, such as hallucinations. In addition to this, we are continually working to improve jailbreak resistance and have recently strengthened the mitigations across Frontier Safety. There may also be occasional slowness or timeout issues. The knowledge cutoff date is January 2025.
For more information about the known limitations for Gemini 3.8 Audio, see the Gemini 3 Pro model card.
Acceptable Usage
For more information about the acceptable usage for Gemini 3.8 Audio, see the Gemini 3 Pro model card.
Ethics and Content Safety
Evaluation Approach
Gemini 3.8 Audio was developed in partnership with internal safety and responsibility teams. A range of evaluations and red teaming activities were conducted to help improve the model and inform decision-making. These evaluations and activities align with Google's AI Principles and responsible AI approach, as well as Google's Generative AI policies (e.g., Generative AI Prohibited Use Policy and the Gemini API Additional Terms of Service).
Evaluation types included but were not limited to:
- Training/Development Evaluations including automated and human evaluations carried out continuously throughout and after the model’s training, to monitor its progress and performance;
- Human Evaluations conducted by specialist teams across the policies and desiderata to ensure the model adheres to safety policies and desired outcomes.
Additional information: For more information about the evaluation approach for Gemini 3.8 Audio, see the Gemini 3 Pro model card.
Safety Policies
For more information about the safety policies for Gemini 3.8 Audio, see the Gemini 3 Pro model card.
Frontier Safety Assessment
Gemini 3.8 Audio is part of the Gemini 3 series of models. To assess Gemini 3.8 Audio for frontier safety, we rely on our evaluations of Gemini 3.7 Flash as outlined in our latest Frontier Safety Framework. We found that Gemini 3.7 Flash did not reach any Tracked or Critical Capability Levels (T/CCLs). Our assessments have shown that Gemini 3.8 Live, Gemini 3.8 Live Extended Thinking, Gemini 3.8 Flash TTS, or Gemini 3.8 Flash-Lite TTS do not have meaningful new capabilities or material increases in performance compared to Gemini 3.7 Flash; therefore, based on Gemini 3.7 Flash results, we are confident that Gemini 3.8 Live, Gemini 3.8 Live Extended Thinking, Gemini 3.8 Flash TTS, or Gemini 3.8 Flash-Lite TTS are not likely to reach any T/CCLs.
For more information on our Frontier Safety Assessment, read the Gemini 3.7 Flash Model Card.
Risks and Mitigations
For more information about the risks and mitigations for Gemini 3.8 Audio, see the Gemini 3 Pro model card.