Azure SpeechSpeech-to-speech

voice-live-pro

JSON

Voice Live Pro S2S GA Provider default streaming, websocket

Voice Live API billing tier applied when the session uses one of its generative models; combines Azure speech recognition, the chosen LLM or native-audio realtime model, and Azure text to speech over WebSocket.

01 Price

$17.00per 1M tokens

Plan or modePrice
azure_speech_standard_audio_output$31.00 per 1M tokens
native_audio_input$32.00 per 1M tokens
native_audio_output$64.00 per 1M tokens
text_input$4.00 per 1M tokens
text_output$16.00 per 1M tokens
text_cached_input$0.40 per 1M tokens
azure_speech_custom_audio_input$40.00 per 1M tokens
azure_speech_custom_audio_output$55.00 per 1M tokens
text_output_2 (gpt-realtime-2, gpt-realtime-2.1)$24.00 per 1M tokens

Base = audio input via Azure Speech (standard), $17 per 1M tokens; per-1M-token rates converted to per-token. Amounts from the Azure Retail Prices API (eastus 'Voice Live API' meters, published per 1K tokens) because the pricing page renders them client-side; same categories as azure.microsoft.com/pricing/details/speech/. The tier is determined by the selected model.

Pricing source, checked 2026-11-18

02 Languages many

Many languages. Azure Speech doesn't list them individually.

03 Features 0 of 19 listed

  • Word timestampsnot listed
  • Speaker diarizationnot listed
  • Punctuationnot listed
  • Profanity filternot listed
  • Custom vocabularynot listed
  • Language detectionnot listed
  • Translationnot listed
  • Sentimentnot listed
  • PII redactionnot listed
  • Summarizationnot listed
  • Topic detectionnot listed
  • Emotion controlnot listed
  • Voice cloningnot listed
  • Voice designnot listed
  • SSMLnot listed
  • Phoneme inputnot listed
  • Speed / prosody controlnot listed
  • Style controlnot listed
  • Multi-speakernot listed

"Not listed" means the provider's data doesn't mention it, not that the model lacks it.

04 Get this record

curl https://voicedex.dev/v1/providers/azure/models/voice-live-pro

Free, no key needed. Use model id voice-live-pro with Azure Speech's own API. API reference.

Esc

↑↓ move↵ open