Baidu AI Cloud SpeechSpeech-to-text

qianfan-asr-v1

JSON

Qianfan ASR v1 (speech recognition LLM) STT Beta streaming, batch, http, websocket

Baidu's large-model speech recognizer behind the realtime, short-utterance, file and fast-file LLM ASR APIs, tuned for multilingual, dialect, accented and noisy speech.

01 Price

¥0.9per hour

Free tier: 10 hours on sign-up.

Plan or modePrice
short utterance (一句话识别大模型), postpaid¥0.00095 per request
file transcription (音频文件转写大模型), postpaid¥0.7 per hour
fast file transcription (极速版), postpaid¥0.78 per hour
realtime prepaid pack 50 h¥0.88 per hour
realtime prepaid pack 1,000 h¥0.85 per hour
realtime prepaid pack 10,000 h¥0.82 per hour
realtime prepaid pack 100,000 h¥0.78 per hour
realtime prepaid pack 500,000 h¥0.72 per hour
short utterance prepaid pack 30k¥0.00093 per request
short utterance prepaid pack 1M¥0.0009 per request
short utterance prepaid pack 10M¥0.00085 per request
short utterance prepaid pack 100M¥0.0008 per request
short utterance prepaid pack 1B¥0.00076 per request
file prepaid pack 50 h¥0.68 per hour
file prepaid pack 1,000 h¥0.66 per hour
file prepaid pack 10,000 h¥0.63 per hour
file prepaid pack 100,000 h¥0.6 per hour
file prepaid pack 500,000 h¥0.56 per hour
fast file prepaid pack 50 h¥0.75 per hour
fast file prepaid pack 1,000 h¥0.72 per hour
fast file prepaid pack 10,000 h¥0.69 per hour
fast file prepaid pack 100,000 h¥0.65 per hour
fast file prepaid pack 500,000 h¥0.62 per hour

Base price = realtime LLM ASR postpaid ¥0.9/hour of audio. Prepaid packs valid one year. Free trial (personal-verified accounts): realtime 10 h, short 50k calls, file 10 h, fast file 10 h (enterprise: short 100k).

Pricing source, checked 2026-11-18

02 Languages

Not published.

03 Features 2 of 11 listed

  • Word timestampsnot listed
  • Speaker diarizationnot listed
  • Punctuation
  • Profanity filter
  • Custom vocabularynot listed
  • Language detectionnot listed
  • Translationnot listed
  • Sentimentnot listed
  • PII redactionnot listed
  • Summarizationnot listed
  • Topic detectionnot listed

"Not listed" means the provider's data doesn't mention it, not that the model lacks it.

04 Get this record

curl https://voicedex.dev/v1/providers/baidu/models/qianfan-asr-v1

Free, no key needed. Use model id qianfan-asr-v1 with Baidu AI Cloud Speech's own API. API reference.

Esc

↑↓ move↵ open