GeekRadar / Il banco di confronto
CONFRONTA.
Modelli IA
openai

GPT Realtime Whisper

Modello IA Uscita

Modalità API
Trascrizione audio*
Finestra di contesto
16.000 tokens
Output massimo
2.000 tokens
Pesi aperti
No

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

GPT Realtime Whisper

Pesi chiusi. Non sono pubblicati un impiego locale supportato o requisiti GPU.

Capacità

Finestra di contesto
16.000 tokens
Output massimo
2.000 tokens
Ragionamento
No
Uso di strumenti
No
Pesi aperti
No
Modalità API
Trascrizione audio*
Input audio
Sì*

Modalità di input

  • audio

Modalità di output

  • text

Configurazione di sistema

Specifiche dettagliate

Specifiche · 7 campi
input cost per second
0,000283333333333*
Ambito e condizioni
native_context
provider
openai*
mode
audio_transcription*
full_native_model_id
gpt-realtime-whisper*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
openai*
Ambito e condizioni
native_context
provider
openai*
mode
audio_transcription*
full_native_model_id
gpt-realtime-whisper*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
audio_transcription*
Ambito e condizioni
native_context
provider
openai*
mode
audio_transcription*
full_native_model_id
gpt-realtime-whisper*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supported endpoints
  • /v1/realtime*
  • /v1/realtime/transcription_sessions*
Ambito e condizioni
native_context
provider
openai*
mode
audio_transcription*
full_native_model_id
gpt-realtime-whisper*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supported modalities
  • audio*
Ambito e condizioni
native_context
provider
openai*
mode
audio_transcription*
full_native_model_id
gpt-realtime-whisper*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supported output modalities
  • text*
Ambito e condizioni
native_context
provider
openai*
mode
audio_transcription*
full_native_model_id
gpt-realtime-whisper*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports audio input
Sì*
Ambito e condizioni
native_context
provider
openai*
mode
audio_transcription*
full_native_model_id
gpt-realtime-whisper*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*

* Dati provvisori