iFlytek launches SparkAudio 1.0 API service
iFlytek announced that SparkAudio 1.0 is available through API services on the iFlytek Open Platform for developers and enterprise users to access directly. According to IT之家, the model accepts text and speech inputs and produces text output, supporting transcription, multilingual translation, dialect recognition, environmental-sound understanding, speaker separation, sentiment analysis and complex audio question answering. The reports attribute support for 99 languages and 202 dialects to iFlytek; no independent test results were provided.
The API release makes SparkAudio 1.0 directly accessible for application development and enterprise use, while providing access to a speech model that iFlytek says supports 99 languages and 202 dialects.