Alibaba (Qwen) / fun-asr
FunASR stands out for General-purpose speech recognition and Built for file transcription at scale. It is best suited to recording transcription and captions and searchable audio.
Context
—
Not applicable
Audio input
$0.000028
/ second
Output
Included
Quality
#88
Elo 1012
Overview
FunASR stands out for General-purpose speech recognition and Built for file transcription at scale. It is best suited to recording transcription and captions and searchable audio.
Audio input
Can process audio input as part of speech or multimodal workflows.
Model maker
Alibaba (Qwen)
Called through SeaLink's unified account, balance, and OpenAI-compatible API.
Protocol
Audio API
Base URL: https://api.sealink.io/v1
Pricing
The final charge follows generated usage and the applicable selector, such as resolution, duration, input type, or provider unit.
API
model
fun-asrbase_url
https://api.sealink.io/v1Auth
Bearer $SEALINK_API_KEYcurl https://api.sealink.io/v1/audio/transcriptions \-H "Authorization: Bearer $SEALINK_API_KEY" \-F model="fun-asr" \-F file_url="https://raw.githubusercontent.com/Jakobovski/free-spoken-digit-dataset/master/recordings/1_jackson_0.wav"
import requestsresp = requests.post("https://api.sealink.io/v1/audio/transcriptions",headers={"Authorization": "Bearer <your-sealink-key>"},data={"model": "fun-asr", "file_url": "https://raw.githubusercontent.com/Jakobovski/free-spoken-digit-dataset/master/recordings/1_jackson_0.wav"},)resp.raise_for_status()print(resp.json()["text"])
const form = new FormData();form.append("model", "fun-asr");form.append("file_url", "https://raw.githubusercontent.com/Jakobovski/free-spoken-digit-dataset/master/recordings/1_jackson_0.wav");const resp = await fetch("https://api.sealink.io/v1/audio/transcriptions", {method: "POST",headers: { Authorization: `Bearer ${process.env.SEALINK_API_KEY}` },body: form,});console.log((await resp.json()).text);