soniox/stt-async-v4

Modello IA

Modalità API: Trascrizione audio^*
Output massimo: 8.000 tokens^*

Non sono ancora disponibili benchmark associati a questa scheda.

Esecuzione locale

Inferenza · stima della memoria

soniox/stt-async-v4

Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.

Capacità

Output massimo: 8.000 tokens^*
Modalità API: Trascrizione audio^*
Input audio: Sì^*

Configurazione di sistema

Specifiche dettagliate

Specifiche · 8 campi

input cost per second

0,0^*

Ambito e condizioni

native_context

provider: soniox^*
mode: audio_transcription^*
full_native_model_id: soniox/stt-async-v4^*
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

soniox^*

Ambito e condizioni

native_context

provider: soniox^*
mode: audio_transcription^*
full_native_model_id: soniox/stt-async-v4^*
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.^*

max output tokens

8.000^*

Ambito e condizioni

native_context

provider: soniox^*
mode: audio_transcription^*
full_native_model_id: soniox/stt-async-v4^*
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.^*

max tokens

8.000^*

Ambito e condizioni

native_context

provider: soniox^*
mode: audio_transcription^*
full_native_model_id: soniox/stt-async-v4^*
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: soniox^*
mode: audio_transcription^*
full_native_model_id: soniox/stt-async-v4^*
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.^*

output cost per second

2,77778e-5^*

Ambito e condizioni

native_context

provider: soniox^*
mode: audio_transcription^*
full_native_model_id: soniox/stt-async-v4^*
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/audio/transcriptions^*

Ambito e condizioni

native_context

provider: soniox^*
mode: audio_transcription^*
full_native_model_id: soniox/stt-async-v4^*
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: soniox^*
mode: audio_transcription^*
full_native_model_id: soniox/stt-async-v4^*
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