Azure Voice Live Pricing Calculator

The Azure Voice Live API is a fully managed solution that enables low-latency, high-quality speech-to-speech interactions for voice agents. It integrates speech recognition, generative AI, and text-to-speech into a single, unified interface — eliminating the need to manually orchestrate multiple components.

Developers provide audio input and receive audio output, avatar visuals, and action triggers — all with minimal latency. You don’t need to deploy or manage any generative AI models; the API handles the underlying infrastructure.

Azure Voice Live supports a broad range of generative AI models including GPT-5, GPT-4.1, GPT-4o, Phi, and gpt-realtime variants. The model you choose determines your pricing tier (Pro, Standard, or Lite).

• Broad locale coverage: Supports 140+ locales for speech-to-text and 600+ standard voices across 150+ locales for text-to-speech.
• Customizable input & output: Use phrase lists, custom speech models, and custom voices to tailor the experience.
• Flexible AI models: Choose from GPT-5, GPT-4.1, GPT-4o, Phi, gpt-realtime, and more.
• Advanced conversational features: Noise suppression, echo cancellation, interruption detection, and end-of-turn detection.
• Avatar integration: Standard or customizable avatars synchronized with audio output.
• Function calling: External actions, tools, and grounded responses via the VoiceRAG pattern.

Pricing is tiered based on the generative AI model used. You don’t select a tier — you choose a model and the corresponding pricing applies:

• Azure Voice Live Pro: gpt-realtime, gpt-4o, gpt-4.1, gpt-5, gpt-5-chat
• Azure Voice Live Standard: gpt-realtime-mini, gpt-4o-mini, gpt-4.1-mini, gpt-5-mini
• Azure Voice Live Lite: gpt-5-nano, phi4-mm-realtime, phi4-mini

Each tier has separate per-token rates for text, Azure Speech Standard audio, Azure Speech Custom audio, and native audio (speech-to-speech). Cached input tokens from earlier turns in a conversation are charged at significantly reduced rates.

Custom voice training/hosting and avatar costs are billed separately.

• Contact centers: Interactive voice bots for customer support, product catalog navigation, and self-service solutions.
• Automotive assistants: Hands-free, in-car voice assistants for commands, navigation, and general inquiries.
• Education: Voice-enabled learning companions and virtual tutors for interactive training.
• Public services: Voice agents for administrative queries and public service information.
• Human resources: Voice-enabled tools for employee support, career development, and training.