Azure/azure-sdk-for-python azure-ai-projects_2.10.0

on GitHub

2.10.0 (2026-10-30)

Features Added

• Added optional VoiceAgentDefinition.soundscape for built-in background ambience and event cues in telephony calls, with VoiceAgentSoundscapeConfig, VoiceAgentSoundscapeSourceConfig, VoiceAgentSoundscapeTrackConfig, VoiceAgentSoundscapeWorkingTrackConfig, and VoiceAgentSoundscapeSound.
• Added optional VoiceAgentInputTranscription.profanity_filter and VoiceAgentProfanityFilterMode for configuring Azure Speech input-transcript filtering before a session starts.
• Added VoiceAgentInputTranscriptionModel.AZURE_SPEECH_STREAMING for Azure Speech streaming transcription in cascaded text-model conversations. This model requires a nonempty VoiceAgentInputTranscription.language and is not supported with realtime speech-to-speech models.
• Added VoiceAgentNoiseReductionType.AZURE_DEEP_NOISE_SUPPRESSION_HEADSET and VoiceAgentNoiseReductionType.AZURE_PERSONAL_NOISE_SUPPRESSION for local voice activity detection without changing recognition audio.
• Added AgentEndpointProtocol.VOICE_CONVERSATION_ENGINE for hosted text agents used as Voice Agent conversation engines. Hosted agents must declare this protocol with version 1.0.0; invocations_ws does not substitute for it.
• Added optional HostedAgentDefinition.enable_memory_snapshot to start hosted-agent sessions from a snapshot of the initialized process instead of starting the process from its image.
• Added known ImageGenTool.model values gpt-image-2.5-sunburst, gpt-image-2.5-sunburst-2026-09-08, gpt-image-2.5-flare, and gpt-image-2.5-flare-2026-09-08, with xhigh and max quality options for these models.

Bugs Fixed

• Fixed tracing to record temperature=0 and top_p=0 instead of omitting these valid values.
• Fixed SimulationSeedDataGenerationJobConfiguration to expose the service-required max_samples property and constructor argument. Updated the simulation-seed evaluation sample to pass this argument directly instead of using the mapping workaround.