---
title: "Generate speech from text (Lightning Large)"
method: POST
path: "/api/v1/lightning-large/stream"
tags: ["Lightning Large"]
---

# Generate speech from text (Lightning Large)

`POST /api/v1/lightning-large/stream`

Converts provided text to speech using the Lightning Large model.

## Request body

- LightningLargeRequest
  - `text` string, required — The text to convert to speech.
  - `voice_id` string, required — The voice identifier to use for speech generation.
  - `sample_rate` integer — The sample rate for the generated audio.
  - `speed` number — The speed of the generated speech.
  - `consistency` number — This parameter controls word repetition and skipping. Decrease it to prevent skipped words, and increase it to prevent repetition.
  - `similarity` number — This parameter controls the similarity between the generated speech and the reference audio. Increase it to make the speech more similar to the reference audio.
  - `enhancement` number — Enhances speech quality at the cost of increased latency.
  - `language` 'en' | 'hi' — Determines how numbers are spelled out. If set to 'en', numbers will be read as individual digits in English. If set to 'hi', numbers will be read as individual digits in Hindi.
  - `output_format` 'pcm' | 'mp3' | 'wav' | 'mulaw' — The format of the output audio.
  - `pronunciation_dicts` string[] — The IDs of the pronunciation dictionaries to use for speech generation.

## Response `200`

Synthesized speech retrieved successfully.

## Other responses

- `400` — Bad request.
- `401` — Unauthorized.
- `500` — Server error occurred.

---

[API](https://skmtc.dev/smallest-inc/apis/waves-api.md) · [All operations](https://skmtc.dev/smallest-inc/apis/waves-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/smallest-inc/waves-api/revisions/cfd5301f2e11/schema)