---
title: "Unified Tts"
method: POST
path: "/v1/speech/synthesize"
tags: ["Unified Agent APIs"]
---

# Unified Tts

`POST /v1/speech/synthesize`

Unified text-to-speech.

Converts text to audio. Deepgram Aura is the primary provider with 105+ voice
models across 7 languages. ElevenLabs is the fallback with premium pre-defined
voices. Returns base64-encoded audio.

For low-latency streaming, use a direct WebSocket connection to the provider.
This endpoint is for batch synthesis (generate audio from text, get result).

## Request body

- SynthesizeRequest
  - `text` string, required
  - `voice_model` string, nullable
  - `voice_id` string, nullable
  - `provider` string, nullable
  - `stability` number
  - `similarity_boost` number

## Response `200`

Successful Response

- unknown

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/suprsonic/apis/suprsonic-unified-agent-api.md) · [All operations](https://skmtc.net/suprsonic/apis/suprsonic-unified-agent-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/suprsonic/suprsonic-unified-agent-api/revisions/2a1b6fcb4ef0/schema)