Google CloudSpeech-to-speech

gemini-2.5-flash-native-audio-preview-12-2025

JSON

Gemini 2.5 Flash Native Audio Preview (12-2025) S2S Beta streaming, websocket

Ends 2027-03-31, 133 days left Google Cloud will shut this model down. Move to gemini-3.8-live. Gemini API deprecations page: shutdown March 31, 2027 (earliest possible retirement date)

Gemini 2.5 Flash Live API preview model with native audio reasoning for bidirectional voice and video agents.

01 Price

$3.00per 1M tokens

Plan or modePrice
audio_output$12.00 per 1M tokens
text_input$0.50 per 1M tokens
text_output$2.00 per 1M tokens

Gemini Developer API paid tier, per 1M tokens: audio/video in $3.00, audio out $12.00, text in $0.50, text out $2.00. Base = audio input.

Pricing source, checked 2026-11-18

02 Languages many

Many languages. Google Cloud 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/google-cloud/models/gemini-2.5-flash-native-audio-preview-12-2025

Free, no key needed. Use model id gemini-2.5-flash-native-audio-preview-12-2025 with Google Cloud's own API. API reference.

Esc

↑↓ move↵ open