Get started
Learn how to use Soniox Speech-to-Text API.
Soniox Speech-to-Text API makes it easy to transcribe and translate speech in over 60 languages with unmatched speed, accuracy, and real-time performance.
Whether you're working with recorded files or live audio streams, Soniox delivers high-quality transcriptions and translations with minimal setup. You can enable advanced features like speaker diarization, context customization, and real-time speech translation through a simple API.
Submit an audio file via a public URL or upload it directly to the API for asynchronous transcription. Receive a complete transcript with speaker labels, timestamps, and confidence scores.
Stream audio live to the Soniox API and receive transcription results with millisecond latency. Real-time mode supports speaker diarization, and context customization.
Stream multilingual speech to the API and receive real-time transcriptions and high-quality translations in over 60 languages with ultra-low latency. Supports speaker separation and two-way translation.