`qwen3-asr-1.7b`

Qwen3 batch ASR. 30 languages. Accepts a prompt.

Native waveform: Language auto or a Qwen code.. Live price and availability are on GET /v1/models/qwen3-asr-1.7b.

Word timestamps have no probability.
Setting timestamp_granularity to word runs a second alignment pass.

Parameters

Field	Type	Description
`params.language` Default auto	string	ISO 639-1 code. auto detects the language. ['ar', 'cs', 'da', 'de', 'el', 'en', 'es', 'fa', 'fi', 'fil', 'fr', 'hi', 'hu', 'id', 'it', 'ja', 'ko', 'mk', 'ms', 'nl', 'pl', 'pt', 'ro', 'ru', 'sv', 'th', 'tr', 'vi', 'yue', 'zh']
`params.response_format` Default json	string	json returns the transcript in result.text. verbose_json also returns language, duration, segments, and words. Word objects do not include probability. When timestamp_granularity is word and this field is omitted, the API sets verbose_json.
`params.timestamp_granularity` Default none	string	none or word. none omits timing. word returns a time range per word and runs a second alignment pass. Omitting the field, or sending null, uses none. word fills response_format to verbose_json when that field is omitted.
`params.prompt`	string	Up to 1000 characters. Context for the transcript: names, vocabulary, or what to listen for.

Example

curl https://api.pascalai.co/v1/speech-to-text \
  -H "Authorization: Bearer $PASCAL_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -F model=qwen3-asr-1.7b \
  -F params='{"prompt":"name, city","language":"en"}' \
  -F file=@input.wav

curl https://api.pascalai.co/v1/speech-to-text/$JOB_ID \
  -H "Authorization: Bearer $PASCAL_API_KEY"