Synthesize parameters

The request body shared by the /speak and /stream endpoints.

Both Synthesize speech and Stream speech accept the same JSON body.

text · string · required

The text to synthesize. Maximum 10,000 characters. Requests over the limit return 400.

language · string

BCP-47 language code, e.g. en, hi, es. Defaults to the voice’s primary_language.

output_format · string · default: "wav"

Output encoding:

Value	Description
wav	Self-contained WAV file (recommended for playback/download).
s16le	Signed 16-bit little-endian PCM (headerless).
s24le	Signed 24-bit little-endian PCM (headerless).
s32le	Signed 32-bit little-endian PCM (headerless).
f32le	32-bit float little-endian PCM (headerless).
f64le	64-bit float little-endian PCM (headerless).

The headerless PCM formats need a known sample_rate and channel count to play.

sample_rate · integer · default: 24000

Output sample rate in Hz. Defaults to the provider’s native rate (24000); values above it are upsampled. The actual rate is returned in the X-Sample-Rate response header (and the start event for streaming).

num_step · integer · default: 32

Number of inference steps, 1–32 - a quality vs. latency trade-off. Provider default (32) if omitted.

expressiveness · number

Style/expressiveness control, 0.0–1.0. Provider default if omitted.

Example body

{
  "text": "The quick brown fox jumps over the lazy dog.",
  "language": "en",
  "output_format": "wav",
  "sample_rate": 24000,
  "expressiveness": 0.5
}