Skip to main content
POST
/
api
/
v1
/
tts
/
speech
Generate Speech
curl --request POST \
  --url https://dev.voice.ai/api/v1/tts/speech \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "<string>",
  "voice_id": "<string>",
  "audio_format": "mp3",
  "temperature": 1,
  "top_p": 0.8,
  "model": "<string>",
  "language": "en"
}
'
"<string>"

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your API key as the bearer token. Format: Authorization: Bearer

Body

application/json
​
text
string
required

The text to generate speech for

​
voice_id
string · null · null

Optional voice ID. If omitted, the default built-in voice is used.

​
audio_format
enum<string> | null
default:mp3

Audio format: mp3, wav, or pcm

Available options:
mp3,
wav,
pcm
​
temperature
number | null
default:1

Temperature for generation (0.0-2.0)

Required range: 0 <= x <= 2
​
top_p
number | null
default:0.8

Top-p sampling parameter (0.0-1.0)

Required range: 0 <= x <= 1
​
model
string · null · null

TTS model to use. Supported models: voiceai-tts-v1-latest, voiceai-tts-v1-2025-12-19 (English only), voiceai-tts-multilingual-v1-latest, voiceai-tts-multilingual-v1-2025-01-14 (multilingual). If not provided, automatically selected based on language at runtime. English ('en') uses non-multilingual models; other languages use multilingual models.

​
language
string
default:en

Language code (ISO 639-1 format). Supported languages: en (English), ca (Catalan), sv (Swedish), es (Spanish), fr (French), de (German), it (Italian), pt (Portuguese), pl (Polish), ru (Russian), nl (Dutch). Defaults to 'en' if not provided.

Response

Successful Response - Returns binary audio file

MP3 audio file