S

Soniox Speech-to-Text API

API service

by Soniox

Speech-to-text API (stt-rt-v5) for real-time and file transcription and speech translation, priced by tokens of audio.

Find alternatives to Soniox Speech-to-Text API

What it does

• Speech to text
• Translation

Features 6

• Automatic language detectionIdentifies the language automatically and follows language changes, even within one sentence.
• Context customizationAccepts terminology, names and custom vocabulary to guide recognition toward the right words.
• Endpoint detectionDetects when a speaker has actually completed a thought, not just paused.
• Real-time speaker diarizationSeparates speakers in real time so every word stays connected to the person who said it.
• Real-time and async modelsOffers STT v5 Real-time for live speech and STT v5 Async for recorded audio and files.
• Regional data residencyProvides in-region processing to meet latency, data residency and regulatory requirements.

Sources

Pricing

Pricing page · 13 Oct 2026

Pricing page read 2026-10-13: token-based; "Equivalent to about $0.10/hour for async (file) and $0.12/hour for real-time (streaming) transcription".

Description

Official documentation · 13 Oct 2026

Pricing and about pages: speech-to-text, text-to-speech and translation in one platform.

What it does

Official documentation · 13 Oct 2026

Pricing and about pages: speech-to-text, text-to-speech and translation in one platform.

Sold within

Pricing page · 13 Oct 2026

Sold on its own with published plans.

Name

Official documentation · 13 Oct 2026

Name as published on the product page.

URL

Official documentation · 13 Oct 2026

Product page, read 2026-10-13.

Deployment

Official documentation · 13 Oct 2026

Hosted API.

Interfaces

Official documentation · 13 Oct 2026

Hosted API.

Also from Soniox

• Soniox App Application

  Soniox App records, transcribes and translates audio.

• Smart Scribe Application

  Smart Scribe records audio and produces real-time transcriptions.

• Soniox Text-to-Speech API API service

  Soniox Text-to-Speech API generates audio from text through a REST endpoint.

• Soniox Speech Translation API API service

  Real-time speech translation API that translates speech one way into a target language, or both ways in a conversation, while people are still speaking, across 60+ languages, for voice agents, live captions and multilingual meetings.

Open Soniox in the directory

Something wrong here? Send a correction — quote this product id: soniox-speech-to-text-api.