Type
Spec
Rate
Input
per 1M audio input tokens
$0.30
Output
per 1M generated tokens
$0.94
Qwen Audio 3.1 ASR and Deepgram Nova-3 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Alibaba Cloud 
Deepgram TranscriptionQwen Audio 3.1 ASR from Alibaba Cloud and Deepgram Nova-3 from Deepgram are both in the Transcription category, available through the EmpirioLabs API.
| Spec | Qwen Audio 3.1 ASR | Deepgram Nova-3 |
|---|---|---|
| Model ID | qwen-audio-3-1-asr | deepgram-nova-3 |
| Author | Alibaba Cloud | Deepgram |
| Released | Sep 10, 2026 | Feb 12, 2025 |
| Input | Audio | Audio |
| Output | Text | Text |
| Region | Singapore | - |
| 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 | Qwen Audio 3.1 ASR | Deepgram Nova-3 |
|---|---|---|
| file | - | string |
| file_url | - | string |
| 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 |
| keyterm | - | string |
| diarize | - | boolean Default: false |
| paragraphs | - | boolean Default: true |
| dictation | - | boolean Default: false |
| punctuate | - | boolean Default: true |
| utterances | - | boolean Default: false |
Send a file as multipart file, or JSON with audio_url or audio_base64, in common audio formats. Short clips and long recordings are both accepted.
The request returns a job_id and a poll_url right away. Poll GET /v1/jobs/<job-id> until status is completed. Short clips finish in seconds; long recordings take longer.
The result of the completed job holds the full transcript as text, sentence segments with start and end times, and word timestamps. The language is detected automatically, including Chinese dialects.
Input and output tokens are priced per 1M, and each request is billed from the usage the model reports.
English, Spanish, French, German, Italian, Portuguese, Japanese, Chinese, Hindi, Russian, Dutch.
Qwen Audio 3.1 ASR 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 qwen-audio-3-1-asr 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": "qwen-audio-3-1-asr",
"audio_url": "https://example.com/meeting-recording.mp3"
}'Prompt tests and comparison runs that cover both models.
Qwen Audio 3.1 ASR is the newer release (Sep 10, 2026); Deepgram Nova-3 was released on Feb 12, 2025. Capabilities listed only for Qwen Audio 3.1 ASR: multilingual. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Qwen Audio 3.1 ASR is the newer release (Sep 10, 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.
