Skip to main content
POST
cURL

Authorizations

xi-api-key
string
header
required

Breeze Developer API key.

Path Parameters

voice_id
string
required

Voice identifier to synthesize. Use GET /v1/voices to discover available IDs.

Query Parameters

output_format
string | null
default:mp3

Audio output format: an encoding (mp3, wav, flac, pcm, aac, opus), optionally followed by a sample rate in Hz and, for mp3, aac and opus, a bitrate in kbps. For example mp3_44100_128, mp3_22050_32, wav_48000, pcm_24000, opus_48000_64. Sample-rate profiles are available for sync and async delivery only. Default: mp3.

delivery
string
default:sync

Use sync for the default audio response, or async to create a background generation job and poll for the result. Async delivery does not bypass concurrent generation limits.

Pattern: ^(sync|async)$

Body

application/json
text
string
required

Text to synthesize.

Minimum string length: 1
model_id
string | null

Optional model identifier to use for synthesis.

Required string length: 1 - 120
language_code
string | null

Optional ISO 639-1 two-letter language code. The selected model must list an explicit code in supported_languages. When omitted, Breeze may attach a high-confidence local detection; otherwise the model handles the text without a language field.

Required string length: 2
Pattern: ^[A-Za-z]{2}$
instructions
string | null

Optional performance instructions for the generation. Use Chinese for Chinese TTS and English for English or any other language. Developer API requests do not translate instructions automatically.

voice_settings
VoiceSettingsPayload · object | null

Optional per-request voice settings override.

Response

Binary audio stream. Content-Type matches the requested output_format.

The response is of type file.