Tencent Hunyuan ASR 3.0 speech-to-text — accurate transcription with word-level timestamps and SRT subtitles, exposed through NovAI's OpenAI-compatible /v1/audio/transcriptions endpoint and billed by real token usage.
curl https://aiapi-pro.com/v1/audio/transcriptions \
-H "Authorization: Bearer $NOVAI_API_KEY" \
-F "model=hy-asr-3.0-preview" \
-F "file=@/path/to/audio.mp3"
curl https://aiapi-pro.com/v1/audio/transcriptions \
-H "Authorization: Bearer $NOVAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "hy-asr-3.0-preview", "file_url": "https://example.com/audio.mp3"}'
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="hy-asr-3.0-preview", 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).
Zero platform fee. Credits never expire. OpenAI-compatible API.
Sign Up Free