Hi everyone, I’m working with OpenAI’s real-time transcription API and noticed that input_audio.input_transcription provides the transcribed text. However, I want to extract the transcription using a different approach—without relying on this built-in property. Are there any other event properties…

You could try storing the audio that gets sent and passing that to the whisper API directly, or to a 3rd party transcription service.

Sure. OpenAI’s speech-to-text engine is called Whisper, and it has its own API endpoint, where you can send audio and receive a transcription, at a significantly lower price than audio inputs sent to GPT-4o-audio models (which are AI for actually doing more thinking and generating AI-powered chat re…

I tried using whisper-1 but the accuracy is not that good even for english too the transcription is not that good so i am looking to get a good accuracy in transcription.

[image] toontown: i am looking to get a good accuracy in transcription Whisper is open-sourced also, so you can use a few different versions of models besides the one choice on OpenAI’s API, such as one for only English, but you would need your own AI inference server or an alternate provider…

Are you using the language parameter to increase accuracy? [image] Arabic Transcription Issue with OpenAI Realtime API Bugs Hi @eng.hello You can fix it simply by adding a language param to the input_audio_transcription object.

Just want to ask one thing is there any audio format which is most suitable to get the perfect output as i am using client server architecture so in which when sending to the backend or for processing it’s in encoded form of base64 "use client"; import { useRef, useCallback } from "react"; import…

[image] toontown: is there any audio format which is most suitable Your code doesn’t show any Whisper usage, it’s just for gpt-4o audio. Again: there is no point in using the realtime API and multimodal AI language models solely for speech-to-text. It is more expensive than Whisper and more …

Actually i am doing something created a voice rag so taking input in voice but theissue in this the transcription doesn’t comes with good accuracy And the code related to whisper is here "use client"; import useWebSocket from "react-use-websocket"; import { useEffect, useRef } from "react"; /**…

With the voice models, there are some options you could play with to increase the ability to transcribe output - and to get good quality output. How about the voice you choose? It is possible that one voice is an easier source for transcriptions, especially considering the variety ranging from male…

Extracting Transcription Without Using input_audio.input_transcription in OpenAI API

API

sps March 11, 2025, 6:10am 7

Are you using the language parameter to increase accuracy?

Topic		Replies	Views
Input_audio_transcription in realtime-api API	5	5582	February 20, 2025
How to setup transcription on Realtime API with SIP API api , realtime , gpt-realtime	30	3560	October 10, 2025
GPT-4o-transcribe and audio model ready to use via API? API transcribe	10	4625	March 17, 2026
Use new model for realtime audio transcription API transcribe	6	3986	June 5, 2025
New audio models in the API + tools for voice agents Announcements	27	7194	July 13, 2025

Extracting Transcription Without Using input_audio.input_transcription in OpenAI API

Related topics