aiqbench analysis
This article details a unified API endpoint for speech-to-text transcription that leverages existing chat infrastructure to eliminate the need for separate SDKs or servers. By supporting multiple Whisper variants and load-balancing across providers, it offers a streamlined approach for developers integrating audio processing directly into their AI workflows. The technical constraints, such as base64 encoding requirements and timeout limits, are clearly defined to assist in system design.
Transcription on OpenRouter
Send base64 audio to POST /api/v1/audio/transcriptions and get JSON text plus a usage object back, with the same API key you already use for chat. Here's the full request contract, the model families, and the limits to design around.
You’ve got a 40-minute sales call recording, a folder of voice memos, or a user holding down a mic button, and you need a text transcript. The usual approach is to stand up a Whisper server or add a second provider SDK just for speech-to-text, on top of whatever already handles your chat traffic. On OpenRouter you can send the audio to POST /api/v1/audio/transcriptions instead and get back JSON with the transcribed text and a usage object, using the same API key and auth as Chat Completions. You don’t need a new SDK or a separate service. Because transcription runs on the same platform as your chat traffic, a model hosted by several providers is load-balanced across them automatically instead of being pinned to a single vendor. Transcribe by sending base64-encoded audio to POST /api/v1/audio/transcriptions and reading JSON text plus a usage object off the response. It takes the same Bearer key as Chat Completions. Whisper models work here: openai/whisper-1, openai/whisper-large-v3, and openai/whisper-large-v3-turbo. Newer token-priced speech-to-text (STT) models exist too. Discover them with ?output_modalities=transcription, not the default catalog. When a transcription…
Excerpt shown under the publisher's RSS terms · 181 words · full text and figures are on the publisher's site
