Skip to main content
POST
Create speech

Authorizations

Authorization
string
header
required

API key as bearer token in Authorization header

Body

application/json

Text-to-speech request input

input
string
required

Text to synthesize

Example:

"Hello world"

model
string
required

TTS model identifier

Example:

"mistralai/voxtral-mini-tts-2603"

input_references
object[]

Reference content for stateless voice cloning: one input_audio part carrying the voice sample, optionally accompanied by one text part with its transcript. Only routed to endpoints that support voice cloning.

Reference content part for stateless voice cloning

Example:
Example:
provider
object

Provider-specific passthrough configuration

response_format
enum<string>
default:pcm

Audio output format

Available options:
mp3,
pcm
Example:

"pcm"

speed
number<double>

Playback speed multiplier. Only used by models that support it (e.g. OpenAI TTS). Ignored by other providers.

Example:

1

voice
string

Voice identifier (provider-specific).

Minimum string length: 1
Example:

"en_paul_neutral"

Response

Audio bytes stream

Raw audio bytestream. Content-Type varies by requested format (audio/mpeg for mp3, audio/pcm for pcm — 16-bit little-endian).