Qwen: Qwen3 ASR Flash
Qwen speech recognition model. Accepts audio via base64 (≤10MB) or a public URL. Transcribed text output is not billed.
Supply channels
Direct official channels with shared authentication, billing and observability. Use the same API key as for other models.
Channels are ordered by request volume over the last 24 hours. A valid public provider name is shown when available; otherwise a generic channel label is used. Availability, latency and throughput use a rolling 24-hour window. Hourly colors show operational, degraded, down or no-traffic periods. Hover for actual values. The price is the same across channels.
Quick start
OpenAI compatible: send input_audio through the chat endpoint and receive the transcription in the response.
import base64
from openai import OpenAI
client = OpenAI(
base_url="https://api.goodputai.cn/v1",
api_key="GOODPUT_API_KEY",
)
with open("speech.wav", "rb") as f:
audio_b64 = base64.b64encode(f.read()).decode()
resp = client.chat.completions.create(
model="qwen/qwen3-asr-flash",
messages=[{
"role": "user",
"content": [{
"type": "input_audio",
"input_audio": {"data": audio_b64, "format": "wav"},
}],
}],
)
print(resp.choices[0].message.content) # Transcription textBilling method：Billed by audio input tokens: CN¥4.40 per million tokens. No separate charge for transcription output.
Related models
Qwen text-to-image model. Billed per successfully generated image at CNY 0.2/image; failed generations are not billed.
Qwen text-to-speech model. Billed by input characters at CNY 0.1 per 1,000 characters. Supports multiple voices via the voice parameter; default: Cherry.
Qwen's visual understanding model with image input and thinking mode.
Add Qwen: Qwen3 ASR Flash to your app
Change the base URL and start calling after you sign up.