Audio

SambaNova’s first speech reasoning model on SambaNova Cloud will extend our multimodal AI capabilities beyond vision to include advanced audio processing and understanding. This model offers OpenAI compatible endpoints that enable real-time reasoning, transcriptions and translations.

The Whisper-Large-v3 model

• Model: Whisper-Large-v3

• Description: State-of-the-art automatic speech recognition (ASR) and translation model. Developed by OpenAI and trained on 5M+ hours of labeled audio. Excels in multilingual and zero-shot speech tasks across diverse domains.

• Model ID: whisper-large-v3

• Supported languages: Multilingual

Core capabilities

• Transcribes and translates extended audio inputs (up to 25 MB).

• Demonstrates high accuracy in speech recognition and translation tasks.

• Provides OpenAI-compatible endpoints for transcriptions and translations.

Request parameters

Parameter	Type	Default	Description	Endpoints
model	String	Required	The ID of the model to use.	transcriptions, translations
prompt	String	Optional	Prompt provided to influence transcription style or vocabulary. Example: “Please transcribe carefully, including pauses and hesitations.”	transcriptions, translations
temperature	Number	0	Sampling temperature between 0 and 1. Higher values increase randomness; lower values produce more focused output.	transcriptions, translations
file	File	Required	Audio file in FLAC, MP3, MP4, MPEG, MPGA, M4A, Ogg, WAV, or WebM format. File size limit: 25 MB	transcriptions, translations
response format	String	JSON	Output format: either JSON or text.	transcriptions, translations
language	String	Optional	The language of the input audio. Supplying the input language in ISO-639-1 (e.g., en) format will improve accuracy and latency.	transcriptions

The Qwen2-Audio Instruct model

• Model: Qwen2-Audio Instruct

• Description: Instruction-tuned large audio language model. Built on Qwen-7B with Whisper-large-v3 audio encoder (8.2B parameters).

• Model ID: qwen2-audio-7b-instruct

• Supported languages: Multilingual

This model is currently being provided as a beta model.

Core capabilities

• Transform audio into Intelligence: Allows you to build GPT-4-like voice applications quickly.

• Provides direct question-answering for any audio input.

• Comprehensive audio processing that includes real-time conversation, transcription, translation, and analysis through a single unified model.

Customization and control

• System-level prompts: Use Assistant Prompt in the request to customize model behavior for specific requirements. See the message parameter in the Request parameters section for more details.

  • Brand-specific formatting (e.g., BrandName vs brandname).

  • Domain-specific terminology.

  • Response style and tone control.

View the Audio reasoning, Translation, and Transcription API endpoint documents for more details.

Audio processing

• Silence detection: Intelligent identification of meaningful pauses and gaps in speech.

• Noise cancellation: Advanced noise filtering and clean audio processing.

• Multilingual processing: Support for multiple languages with automatic language detection.

Analysis capabilities

• Sentiment analysis: Detects and analyzes emotional content in speech.

• Multi-speaker handling: Processes conversations with multiple participants.

• Mixed audio understanding: Comprehends speech, music, and environmental sounds.

Speech recognition performance numbers

• Metrics taken from published Qwen2-Audio paper benchmarks.

• WER%, lower is better

Language	Dataset	Qwen2-Audio	Whisper-large-v3	Improvement
English	Common Voice 15	8.6%	9.3%	+7.5%
Chinese	Common Voice 15	6.9%	12.8%	+46.1%

Request parameters

Parameter	Type	Default	Description	Endpoints
model	String	Required	The ID of the model to use. Only Qwen2-Audio-7B-Instruct is currently available.	All
messages	Message	Required	A list of messages containing role (user/system/assistant), type (text/audio_content), and audio_content (base64 audio content).	All
response_format	String	JSON	The output format, either JSON or text.	All
temperature	Number	0	Sampling temperature between 0 and 1. Higher values (e.g., 0.8) increase randomness, while lower values (e.g., 0.2) make output more focused.	All
max_tokens	Number	1000	The maximum number of tokens to generate.	All
file	File	Required	Audio file in FLAC, MP3, MP4, MPEG, MPGA, M4A, Ogg, WAV, or WebM format. Each single file must not exceed 30 seconds in duration.	All
language	String	Optional	The target language for transcription or translation.	Transcription, Translation
stream	Boolean	False	Enables streaming responses.	All
stream_options	Object	Optional	Additional streaming configuration (e.g., {“include_usage”: true}).	All