Home › Models › WAND ASR v1
Tencent WAND · ASR v1 · Just Added

WAND ASR v1 API

Tencent WAND ASR v1 offers multilingual speech-to-text with automatic language detection and subtitle output, exposed through NovAI's OpenAI-compatible /v1/audio/transcriptions endpoint and billed by real token usage.

$1.54 / 1M
Token rate
≈$0.007
Per min audio (ref)
Auto
Language detect
$0
Platform fee
Sign Up - Get $2.00 Free Credit See All Pricing

Why use WAND ASR v1 on NovAI?

  • Multilingual - transcribe across many languages
  • Auto language detection - no need to specify the source language
  • Subtitles - SRT subtitle_url output with timing
  • File or URL input - multipart upload or a public audio URL
  • OpenAI compatible - drop-in audio.transcriptions SDK usage
  • Token billing - pay only for real upstream token usage

Best use cases

  • Multilingual media transcription
  • Subtitle localization
  • Cross-language meeting notes
  • Voice content indexing
  • Global call-center analytics

Quick start

cURL — multipart file upload

curl https://aiapi-pro.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -F "model=wand-asr-v1" \
  -F "file=@/path/to/audio.mp3"

cURL — JSON with a public audio URL

curl https://aiapi-pro.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "wand-asr-v1", "file_url": "https://example.com/audio.mp3"}'

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI(
    base_url="https://aiapi-pro.com/v1",
    api_key="YOUR_NOVAI_API_KEY",
)
with open("audio.mp3", "rb") as f:
    resp = client.audio.transcriptions.create(model="wand-asr-v1", file=f)
print(resp.text)

Returns text plus sentences (word timestamps), detected language and an SRT subtitle_url. Accepts a multipart file upload or a JSON file_url. Billed by real upstream token usage (usage.total_tokens × $1.54 / 1M).

Try WAND ASR v1 today

Zero platform fee. Credits never expire. OpenAI-compatible API.

Sign Up Free