The API documentation reads: The Speech API provides support for real time audio streaming using chunk transfer encoding. This means that the audio is able to be played before the full file has been generated and made accessible. I am trying since hours to playback chunks of the openai.audio.spe…

For anyone looking to stream audio using the speech api: import pyaudio from openai import OpenAI client = OpenAI() p = pyaudio.PyAudio() stream = p.open(format=8, channels=1, rate=24_000, output=True) with client.audio.speech.with_streaming_respon…

I finally had some time to come back to this and found a pretty simple solution. It’s possible to directly pass the response.raw stream into the wave.open call, which automatically deals with parsing the header and buffering chunks. I’m getting full playback without noise with this: import os from …

@nimobeeren if response.ok: with wave.open(response.raw, 'rb') as wf: p = pyaudio.PyAudio() stream = p.open(format=p.get_format_from_width(wf.getsampwidth()), channels=wf.getnchannels(), rate=wf.getframerate(), …

If you wouldn’t mind could you please elaborate how you’re playing the audio on the front end? I’m not having any luck with it, but my backend is definitely sending it with chunked encoding.

Sure, so there are two parts: Server side is a REST Api with Node.js and Express, something like this: app.get("/api/stream", async (req, res) => { const { text, voice } = req.query; // Assuming the text for TTS is passed as a query parameter generateOpenAIAudio(text, voice, req, res); }); And …

Thank you! Yeah, I was attempting to use a streamed response to make it feel more real-time, but it seems like some browsers don’t play nice with it quite yet. I was attempting to use the MediaSource API to append the chunks as they came in from the server, but it has been anything but straightforw…

Because I don’t see the “stream: true” in your request, can you please explain how this code actually stream the response rather than autoplay once the entire response is ready?

Yes, I’ve found that stream: true doesn’t make a difference in this case. If you use console log to write out when the streaming ends, You’ll see that the audio starts way before the whole response arrives from the API call. At least that’s my experience.

I haven’t tried Greg’s code, but essentially any request to fetch some binary data is “streamed” in the sense that the data is split into chunks which are sent sequentially to the client. The HTML audio element is probably set up to work with those streams by playing the audio as soon as the first c…

[image] stamatis.kourtis: Yup I verify (only javascript) that by setting streaming=“true”, the response is chunked, and thus the delay is reduced significantly. However, because these chunks experience delay variation as they travel the network, you cannot just playback by pushing them in the au…

Streaming from Text-to-Speech api

API

nimobeeren March 4, 2024, 9:35pm 36

Note this GitHub issue which shows an example for streaming TTS output to speakers using the openai Python library.

Topic		Replies	Views
Chat completions audio output but not base64 encoded string API chat-completion , speech	5	424	October 10, 2025
Realtime API extremely expensive Feedback realtime	66	8632	December 4, 2024
How to decrease the latency of Text-To-Speech API? API gpt-4 , api	6	5123	April 26, 2024
Python integration of real time? API	13	4132	October 5, 2024
Connecting to the Realtime API API	45	9301	June 5, 2025

Streaming from Text-to-Speech api

Related topics