Create Voice · Moss API

Request body parameters

FieldTypeRequiredDescription

audio_sample: fileRequired

Local reference audio. Supports wav, mp3, m4a, and flac; maximum file size 10 MB and duration 30 seconds.

name: stringOptional

Voice name.

Return value

FieldTypeDescription

id: string

voice id; referenced by endpoints such as TTS/TTSD.

object: string

Fixed as audio.voice.

name: string

Voice name; may be an empty string when name is not provided.

created_at: integer

Creation time, a Unix timestamp in seconds.

Next steps

Generate Voice

Generate a voice or speech from text and a voice description.

Single-speaker Speech

Text-to-speech endpoint.

Request example

curl -X POST "https://api.mosi.cn/v1/audio/voices" \
  -H "Authorization: Bearer $MOSS_API_KEY" \
  -F "name=customer-service-voice" \
  -F "audio_sample=@./voice-sample.wav"

import os
import requests

with open("./voice-sample.wav", "rb") as audio_sample:
    response = requests.post(
        "https://api.mosi.cn/v1/audio/voices",
        headers={
        "Authorization": f"Bearer {os.environ['MOSS_API_KEY']}",
        },
        data={
            "name": "customer-service-voice",
        },
        files={"audio_sample": audio_sample},
    )

response.raise_for_status()
print(response.json())

import { readFile } from "node:fs/promises"

const bytes = await readFile("./voice-sample.wav")
const form = new FormData()
form.append("name", "customer-service-voice")
form.append("audio_sample", new Blob([bytes]), "voice-sample.wav")

const response = await fetch("https://api.mosi.cn/v1/audio/voices", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.MOSS_API_KEY,
  },
  body: form,
})

if (!response.ok) throw new Error(`HTTP ${response.status}`)
console.log(await response.json())

Response example

{
  "id": "<voice_id>",
  "object": "audio.voice",
  "name": "Alice",
  "created_at": 1710000000
}