Skip to main content
POST
cURL

Continue building

Write instructions

Choose intent, emotion, and delivery.

Speech timing

Build captions with word timing.

Convert text to speech

Generate audio without word timing.

Streaming timestamps

Stream audio with word timing.

Authorizations

xi-api-key
string
header
required

Breeze Developer API key.

Path Parameters

voice_id
string
required

Voice ID to use for speech generation. See List voices.

Query Parameters

output_format
string | null
default:mp3

Audio encoding: mp3, wav, flac, pcm, aac, or opus. Optional sample rate and bitrate profiles follow ordinary synchronous TTS, e.g. wav_48000. Default: mp3. See Output formats.

delivery
string
default:sync

sync (default) returns audio_base64 and word_timestamps. async returns a job ID immediately; poll Get generation job for the result. See Async jobs.

Pattern: ^(sync|async)$

Body

application/json

Speech with complete word timing; ordinary TTS fields only.

text
string
required

Text to synthesize. Up to 1000 characters by default; accounts with an approved higher limit may send up to their configured limit, at most 2000 characters. See Audio tags.

Minimum string length: 1
model_id
string | null

Model ID for speech generation. Selected automatically when omitted. See List models.

Required string length: 1 - 120
language_code
string | null

ISO 639-1 two-letter language code supported by the selected model. See supported language codes.

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

Performance instructions, written in the same language as the input text. See Expressive controls, Voice instruction prompting.

voice_settings
TtsVoiceSettingsPayload · object | null

Optional per-request voice settings override. See Voice settings.

Response

Complete audio and word timestamps. The history-item-id header identifies the saved audio.

audio_base64
string
required

Complete audio encoded as base64. Decode before saving or playback. See Decode audio and timing.

content_type
string
required

MIME type of the decoded audio, matching output_format.

word_timestamps
WordTimestampResponse · object[]
required

Complete word/token list, relative to the delivered audio in seconds. See Speech timing.