Type
Spec
Rate
Transcription
per hour of audio
$0.60
StepAudio 3 ASR Max and Deepgram Nova-3 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
StepFun 
Deepgram TranscriptionStepAudio 3 ASR Max from StepFun and Deepgram Nova-3 from Deepgram are both in the Transcription category, available through the EmpirioLabs API.
| Spec | StepAudio 3 ASR Max | Deepgram Nova-3 |
|---|---|---|
| Model ID | stepaudio-3-asr-max | deepgram-nova-3 |
| Author | StepFun | Deepgram |
| Released | Aug 31, 2026 | Feb 12, 2025 |
| Input | Audio | Audio |
| Output | Text | Text |
| Region | International | - |
| Endpoints | POST /v1/audio/transcriptions | POST /v1/audio/transcriptions |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | StepAudio 3 ASR Max | Deepgram Nova-3 |
|---|---|---|
| file | string | string |
| file_url | string | string |
| audio_base64 | string | - |
| enable_itn | boolean Default: true | - |
| format | wav, mp3, ogg, m4a, pcm | - |
| codec | string | - |
| rate | number | - |
| bits | number | - |
| channel | number | - |
| smart_format | - | boolean Default: true |
| profanity_filter | - | boolean Default: false |
| numerals | - | boolean Default: true |
| measurements | - | boolean Default: false |
| language | - | auto, en, es, fr, de, it, pt, ja, zh, hi, ru, nl Default: auto |
| redact_pii | - | boolean Default: false |
| redact_pci | - | boolean Default: false |
Supports wav, mp3, ogg, m4a, and pcm input. PCM requests should include codec, sample rate, bit depth, and channel count. The language is detected automatically and cannot be set; Chinese, English, Japanese, Korean, French, and Spanish are recognized, with languages other than Chinese and English in preview. Inverse text normalization is on by default and can be turned off with enable_itn. Hotwords and word timestamps are not available on this model. Audio is billed by its measured duration, with a one second minimum.
English, Spanish, French, German, Italian, Portuguese, Japanese, Chinese, Hindi, Russian, Dutch.
StepAudio 3 ASR Max runs through POST /v1/audio/transcriptions. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Both models are called through the same endpoint. Set model to stepaudio-3-asr-max or deepgram-nova-3. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "stepaudio-3-asr-max",
"audio_url": "https://example.com/meeting-recording.mp3"
}'Prompt tests and comparison runs that cover both models.
StepAudio 3 ASR Max is the newer release (Aug 31, 2026); Deepgram Nova-3 was released on Feb 12, 2025. Capabilities listed only for StepAudio 3 ASR Max: multilingual. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
StepAudio 3 ASR Max is the newer release (Aug 31, 2026); Deepgram Nova-3 was released on Feb 12, 2025.
The two models are priced on different units or tiers, so compare the live rate cards on this page. They always match what the API charges.
Yes. Both models use POST /v1/audio/transcriptions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.
