#Response format is not mp3 for openai.fm

1 messages · Page 1 of 1 (latest)

cursive frostBOT
#

Reported by @woeful drum

Bug Report: Response format is not mp3 for openai.fm
`Steps to Reproduce`

Generate any sound, press play or download.

`Expected Result`

Response format is not mp3 for download and play.

`Actual Result`

Play does not work, and downloaded files needs to be renamed to play.

`Environment`

https://openai.fm/ using duckduckgo browser.

#
Additional Information

Please provide relevant details to help resolve the issue, such as:

  • ChatGPT Shared Link (if applicable).
  • Screenshots or videos demonstrating the problem.

-# ➜ Need to contact support? Visit the OpenAI Help Center.

woeful drum
#

import OpenAI from 'openai';
import { playAudio } from 'openai/helpers/audio';

const openai = new OpenAI();

const input = "
"What is Vitalism and a Vitalist?
Current version of Vitalism in one sentence:
Vitalism is the movement to make unlimited lifespans in peak health humanity’s first priority, and to reflect that in budgets, policies and culture.
A Vitalist is defined as someone who agrees with the Vitalist Declaration:

  1. Life and health are good. Death is humanity’s core problem, and aging its primary agent.
  2. Aging causes immense suffering, and obviating aging is scientifically plausible.
  3. Humanity should apply the necessary resources to reach freedom from aging as soon as possible.
  4. I will work on or support others to work on reaching unlimited healthy human lifespan.
  5. I will carry the message against aging and death."

A Vitalist wants to end biological aging and death."
";

const instructions = "Tone: The voice should be refined, formal, and delightfully theatrical, reminiscent of a charming radio announcer from the early 20th century.\n\nPacing: The speech should flow smoothly at a steady cadence, neither rushed nor sluggish, allowing for clarity and a touch of grandeur.\n\nPronunciation: Words should be enunciated crisply and elegantly, with an emphasis on vintage expressions and a slight flourish on key phrases.\n\nEmotion: The delivery should feel warm, enthusiastic, and welcoming, as if addressing a distinguished audience with utmost politeness.\n\nInflection: Gentle rises and falls in pitch should be used to maintain engagement, adding a playful yet dignified flair to each sentence.\n\nWord Choice: The script should incorporate vintage expressions like splendid, marvelous, posthaste, and ta-ta for now, avoiding modern slang.";

const response = await openai.audio.speech.create({
model: 'gpt-4o-mini-tts',
voice: 'sage',
input,
instructions,
});

await playAudio(response);

https://platform.openai.com/docs/guides/text-to-speech