---
title: "OpenRouter Launches Audio Transcription API with Unified Endpoint for Speech-to-Text"
source: "OpenRouter：Announcements（RSS）"
source_tier: "t1"
url: "https://openrouter.ai/blog/tutorials/transcription-on-openrouter/"
permalink: "https://feed.astralor.com/items/itm_38c1c638feb3dec92af71ea8"
published: "2026-07-22T00:00:00.000Z"
score: 82
channel: "ai"
tags: ["API","OpenRouter","speech recognition","Audio Transcription"]
---

# OpenRouter Launches Audio Transcription API with Unified Endpoint for Speech-to-Text

## AI commentary

> This update is worth noting, especially for teams building voice apps who want to avoid vendor lock-in. OpenRouter's unified routing reduces model selection and deployment complexity, and it's likely to add more multimodal capabilities soon. If you're an indie developer or a small SaaS team, this could become a handy addition to your toolkit.

## At a glance

OpenRouter has added an audio transcription feature, accessible via a single POST endpoint /api/v1/audio/transcriptions. Developers send base64-encoded audio and receive JSON text plus usage data. This lowers the barrier for integrating speech recognition, eliminating the need to manage multiple models. It currently supports common audio formats, with potential expansion to more languages and models.

## Key points

- New POST /api/v1/audio/transcriptions endpoint for audio transcription.
- Input: base64-encoded audio; Output: JSON text with usage object.
- Unified API reduces complexity of managing multiple speech-to-text models.

## Full text

Transcribe speech to text on OpenRouter through one endpoint: POST /api/v1/audio/transcriptions. Send base64 audio, get JSON text plus a usage object back.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_38c1c638feb3dec92af71ea8