gemini-3.1-flash-live-previewGemini 3.1 Flash Live Preview is a audio model from Google, available through SilixarCloudInc for commercial speech recognition, transcription, and synthesis. Google's preview audio-to-audio model for low-latency, voice-first applications with multimodal input and tool use. The serving profile supports a 128K context window and up to 64K output tokens. The published license is Commercial API terms.
Gemini 3.1 Flash Live Preview is a audio model from Google, available through SilixarCloudInc for commercial speech recognition, transcription, and synthesis. Google's preview audio-to-audio model for low-latency, voice-first applications with multimodal input and tool use. The serving profile supports a 128K context window and up to 64K output tokens. The published license is Commercial API terms.
Use the published identifier and pricing on this page.
Tell us your expected workload and billing requirements.
We confirm access and onboarding instructions by email.
Related models are ordered by provider, category, and release date.
GoogleAudioGoogleVisionGoogleVideoGoogleVisionGoogleImageGoogleImageKey facts about Gemini 3.1 Flash Live Preview, its pricing, capabilities, and access through SilixarCloudInc.
Gemini 3.1 Flash Live Preview is a audio model from Google, available through SilixarCloudInc for commercial speech recognition, transcription, and synthesis. Google's preview audio-to-audio model for low-latency, voice-first applications with multimodal input and tool use. The serving profile supports a 128K context window and up to 64K output tokens. The published license is Commercial API terms.
Use gemini-3.1-flash-live-preview as the model identifier when configuring this model through SilixarCloudInc.
Input at $0.005 per Audio minute, Output at $0.018 per Audio minute. Charges follow recorded usage and the billing unit shown above.
The current serving profile supports Serverless, Image input, Tools. Capabilities marked as not supported are not included in this published profile.
The published context length is 128K, and the maximum output is 64K.
Select “Use this model” and contact SilixarCloudInc at post@silixarcloudinc.com. We will confirm availability, account setup, and integration details by email.
Contact SilixarCloudInc for model availability, account setup, and integration details.