Transcription / MODEL API
Qwen3-ASR-1.7B
Input $0.05 / 1M tokens
OVERVIEW
Model overview
The Qwen3-ASR family includes Qwen3-ASR-1.7B and Qwen3-ASR-0.6B, which support language identification and ASR for 52 languages and dialects. Both leverage large-scale speech training data and the strong audio understanding capability of their foundation model, Qwen3-Omni. Experiments show that the 1.7B version achieves state-of-the-art performance among open-source ASR models and is competitive with the strongest proprietary commercial APIs.
Specifications
- Category
- Transcription
- Input modalities
- audio
- Output modalities
- text
MODEL PRICING
Model API pricing
Transcription
USD per 1M tokens| Model | Input | Output |
|---|---|---|
| Qwen3-ASR-1.7B | $0.05 | — |
Public platform rates refresh every five minutes. A dash means a rate is not provided; it does not mean free. Check the console for final charges.
BUILT FOR YOUR STACK
API quickstart
Expand connection setup and run the preparation commands first. Then save and run the Python or cURL example.
Connection setup & preparationActual API address, model ID, and environment variables
- API address
https://api.ecohash.com/v1- API model ID
qwen3-asr-1-7b
Replace YOUR_API_KEY with the full inference API key issued in the console. Run setup in macOS/Linux or a compatible shell. JSON cURL examples use the Python standard library to build the request body.
python -m pip install openai
export GIGACOMMA_API_BASE_URL='https://api.ecohash.com/v1'
export GIGACOMMA_MODEL_ID='qwen3-asr-1-7b'
export GIGACOMMA_API_KEY="YOUR_API_KEY"GIGACOMMA_API_KEY is the environment variable name. Its value is an inference API key from the console, not an OpenAI API key. Get an API key
Prepare this local audio file before running the example: audio.mp3
import osfrom openai import OpenAIMODEL_ID = os.environ["GIGACOMMA_MODEL_ID"]client = OpenAI( base_url=os.environ["GIGACOMMA_API_BASE_URL"], api_key=os.environ["GIGACOMMA_API_KEY"],)with open("audio.mp3", "rb") as audio: response = client.audio.transcriptions.create( model=MODEL_ID, file=audio, )print(response.text)