Audio to text model
nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b
nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b is an audio-to-text model available through the LLM7 API at /v1/audio/transcriptions. It supports audio input, speech transcription and returns text with the detected language, audio duration, and timed segments. Billing is based on input audio duration. Current pricing is available below.
nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6bCurrent LLM7 pricing
Simple, pay-as-you-go pricing
Checking current pricing…
Start building
A verified request for this exact model. Add your API key and run it.
curl https://api.llm7.io/v1/audio/transcriptions \
-H "Authorization: Bearer $LLM7_API_TOKEN" \
-F "model=nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b" \
-F "file=@recording.mp3" \
-F "response_format=json"