Build Smarter Agents with Nemotron 3 Nano Omni on FriendliAI — Explore models
API Reference
Model APIs
Dedicated
Container
Dataset & File
BetaFriendli SDK
curl --request POST \
--url http://localhost:8000/v1/audio/transcriptions \
--header 'Content-Type: multipart/form-data' \
--form file='@example-file'{
"text": "Hello, how are you?",
"usage": {
"type": "tokens",
"input_tokens": 20,
"output_tokens": 10,
"total_tokens": 30,
"input_audio_length_ms": 18000,
"processed_audio_length_ms": 24000,
"input_token_details": {
"audio_tokens": 10,
"text_tokens": 10
}
}
}Container audio transcriptions
Transcribe audio files to text using Friendli Container. Run speech-to-text models locally on your own GPU hardware with full data privacy.
curl --request POST \
--url http://localhost:8000/v1/audio/transcriptions \
--header 'Content-Type: multipart/form-data' \
--form file='@example-file'{
"text": "Hello, how are you?",
"usage": {
"type": "tokens",
"input_tokens": 20,
"output_tokens": 10,
"total_tokens": 30,
"input_audio_length_ms": 18000,
"processed_audio_length_ms": 24000,
"input_token_details": {
"audio_tokens": 10,
"text_tokens": 10
}
}
}Given an audio file, the model transcribes it into text.Documentation Index
Fetch the complete documentation index at: https://friendli.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
Body
The audio file object (not file name) to transcribe, in one of these formats: mp3, wav, flac, ogg, and many other standard audio formats.
Routes the request to a specific adapter.
"(adapter-route)"
Controls how the audio is cut into chunks. When set to "auto", the server first normalizes loudness and then uses voice activity detection (VAD) to choose boundaries. server_vad object can be provided to tweak VAD detection parameters manually. If unset, the audio is transcribed as a single block.
"auto"Whether to stream the transcription result. When set to true, the transcription result will be streamed as server-sent events once generated.
The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
Response
Successfully transcribed the audio file.
The transcribed text.
Hide child attributes
Hide child attributes
The type of the usage object. Always tokens for this variant.
"tokens"Number of input tokens billed for this request.
Number of output tokens generated.
Total number of tokens used (input + output).
The length of the input audio in milliseconds.
The length of the processed audio in milliseconds.