---
title: "Voice Cloned TTS Stream"
method: POST
path: "/api/v1/tts/sse"
---

# Voice Cloned TTS Stream

`POST /api/v1/tts/sse`

## Request

- Base URL: `https://api.vachana.ai`
- URL: `https://api.vachana.ai/api/v1/tts/sse`
- Auth: API key in header `X-API-Key-ID`
- TypeScript: <https://skmtc.dev/gnani/apis/vachana-speech-to-text-api/docs/api/v1/tts/sse/post.ts> (a function with typed inputs; its response is checked against the schema)

## Headers

- `X-API-Key-ID` string, required

## Request body

- VoiceCloneRequest: Request body for voice cloned TTS inference.
  - `text` string, required: The text to synthesize into speech.
  - `model` 'vachana-vc-v1': Supported voice cloning model.
  - `speaker_embedding` SpeakerEmbedding, required: Voice clone embedding obtained from the Voice Clone Embeddings endpoint.
    - `embedding` string, required: The base64-encoded voice clone embedding tensor.
    - `shape` integer[], required: Shape of the embedding tensor, e.g. [1, 768].
    - `dtype` string, required: Data type of the embedding tensor, e.g. torch.bfloat16.
  - `audio_config` AudioConfig, required: Audio output configuration.
    - `sample_rate` integer: Sample rate in Hz
    - `num_channels` integer: Number of audio channels
    - `sample_width` integer: Sample width in bytes
    - `encoding` 'linear_pcm' | 'oggopus': Supported audio encodings.
    - `container` 'raw' | 'mp3' | 'wav' | 'mulaw' | 'ogg': Supported audio containers.
    - `bitrate` '96k' | '128k' | '192k': Supported MP3 bitrate options (only used when container is mp3).

## Response `200`

Successful Server-Sent Events stream

## Other responses

- `400`: Bad Request
- `429`: Too Many Requests
- `500`: Internal Server Error
- `503`: Service Unavailable

---

[API](https://skmtc.dev/gnani/apis/vachana-speech-to-text-api.md) - [All operations](https://skmtc.dev/gnani/apis/vachana-speech-to-text-api/llms.txt) - [OpenAPI document](https://skmtc.dev/gnani/apis/vachana-speech-to-text-api/revisions/d9f838824278?raw)