Audio - pre.dev

Both endpoints take the OpenAI-compatible speech and transcription request bodies and return the matching responses. Speech and transcription models appear in the main catalog; pick an id whose row lists the audio modality.

Text to speech

POST /v1/audio/speech takes a JSON body and returns audio bytes.

curl --fail-with-body https://api.pre.dev/v1/audio/speech \
  -H "Authorization: Bearer $PREDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"model\": \"$SPEECH_MODEL\", \"input\": \"Your build is ready.\", \"voice\": \"alloy\"}" \
  -o ready.mp3

import fs from 'node:fs/promises';
import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://api.pre.dev/v1', apiKey: process.env.PREDEV_API_KEY! });

const speech = await client.audio.speech.create({
  model: process.env.SPEECH_MODEL!,
  input: 'Your build is ready.',
  voice: 'alloy',
});
await fs.writeFile('ready.mp3', Buffer.from(await speech.arrayBuffer()));

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.pre.dev/v1", api_key=os.environ["PREDEV_API_KEY"])

with client.audio.speech.with_streaming_response.create(
    model=os.environ["SPEECH_MODEL"],
    input="Your build is ready.",
    voice="alloy",
) as speech:
    speech.stream_to_file("ready.mp3")

Transcription

POST /v1/audio/transcriptions is multipart/form-data with a file part and a model field.

curl --fail-with-body https://api.pre.dev/v1/audio/transcriptions \
  -H "Authorization: Bearer $PREDEV_API_KEY" \
  -F "model=$TRANSCRIBE_MODEL" \
  -F "file=@meeting.m4a"

import fs from 'node:fs';
import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://api.pre.dev/v1', apiKey: process.env.PREDEV_API_KEY! });

const transcript = await client.audio.transcriptions.create({
  model: process.env.TRANSCRIBE_MODEL!,
  file: fs.createReadStream('meeting.m4a'),
});
console.log(transcript.text);

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.pre.dev/v1", api_key=os.environ["PREDEV_API_KEY"])

with open("meeting.m4a", "rb") as audio:
    transcript = client.audio.transcriptions.create(model=os.environ["TRANSCRIBE_MODEL"], file=audio)
print(transcript.text)

Set SPEECH_MODEL and TRANSCRIBE_MODEL to ids from the catalog. Available voices, formats, and other fields depend on the model; check its catalog row. Both calls return the usual x-predev-* headers and are billed from usage.cost.