Text to Speech

Convert text to lifelike audio with sonus-tts in four output formats.

POST https://api.sagea.space/v1/audio/speech

Authentication

Send Authorization: Bearer $SAGEA_API_KEY on every request. Get a key

Parameters

Send a JSON body with the following fields.

Parameter	Type	Required	Description
`model`	`string`	Yes	Always `sonus-tts` for speech synthesis.
`input`	`string`	Yes	Text to synthesize, max 4096 characters per request.
`voice`	`string`	No	One of `nova`, `atlas`, or a cloned `voice_id`.
`response_format`	`string`	No	One of `mp3`, `wav`, `ogg`, or `flac`. Default is `mp3`.
`emotion`	`string`	No	One of `neutral`, `friendly`, `professional`, `excited`, `calm`, or `warm`.
`speed`	`number`	No	Playback speed from 0.5 to 2.0. Default is `1.0`.
`language`	`string`	No	BCP-47 hint such as `ne-NP`, `hi-IN`, `en-US`, or `es-ES`.

Example request

Synthesize Welcome to SAGEA plus a ne-NP greeting with voice nova.

curl -X POST https://api.sagea.space/v1/audio/speech \
  -H "Authorization: Bearer $SAGEA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonus-tts",
    "input": "Welcome to SAGEA. नमस्ते, SAGEA मा स्वागत छ।",
    "voice": "nova",
    "response_format": "mp3",
    "emotion": "friendly",
    "speed": 1.0
  }' \
  --output welcome.mp3

Response

The API returns binary audio bytes with content type matching the format.

{
  "note": "Binary audio response, not JSON. Headers show format and size.",
  "content_type": "audio/mpeg",
  "content_length": 48210,
  "request_id": "tts_8welcomenp01",
  "model": "sonus-tts",
  "voice": "nova"
}

Save the body as welcome.mp3 and play it locally to verify output.

Errors

Status	Code	Fix
`400`	`text_too_long`	Split `input` into chunks under 4096 characters.
`400`	`unsupported_format`	Use one of `mp3`, `wav`, `ogg`, or `flac`.
`401`	`unauthorized`	Re-export a valid `SAGEA_API_KEY` value.
`422`	`voice_not_found`	Use `nova`, `atlas`, or a valid `vox_` voice ID.
`429`	`rate_limit_exceeded`	Back off and retry with exponential delay.

Limits

Sonus TTS allows 50 requests per minute on Starter and 500 requests per minute on Pro.