---
title: "Text-to-speech synthesis"
method: POST
path: "/voice/v1/speak"
tags: ["Voice"]
---

# Text-to-speech synthesis

`POST /voice/v1/speak`

Convert text to natural-sounding audio using ElevenLabs voices. Ideal for creating audio summaries of legal documents, client presentations, or accessibility features. Supports multiple languages and voice customization.

## Request body

- object
  - `text` string, required — Text to convert to speech
  - `voice_id` string — ElevenLabs voice ID (defaults to Rachel - professional, clear)
  - `model_id` 'eleven_multilingual_v2' | 'eleven_turbo_v2' | 'eleven_monolingual_v1' — ElevenLabs model ID
  - `output_format` 'mp3_44100_128' | 'mp3_44100_192' | 'pcm_16000' | 'pcm_22050' | 'pcm_24000' | 'pcm_44100' — Audio output format
  - `voice_settings` object — Voice customization settings
    - `stability` number — Voice stability (0-1)
    - `similarity_boost` number — Similarity boost (0-1)
    - `style` number — Style exaggeration (0-1)
    - `use_speaker_boost` boolean — Enable speaker boost
  - `language_code` string — Language code for multilingual models
  - `optimize_streaming_latency` integer — Optimize for streaming latency (0-4)
  - `enable_logging` boolean — Enable request logging
  - `seed` integer — Seed for reproducible generation
  - `previous_text` string — Previous context for better pronunciation
  - `next_text` string — Next context for better pronunciation
  - `apply_text_normalization` boolean — Apply automatic text normalization

## Response `200`

Audio file generated successfully

## Other responses

- `400` — Invalid request - missing or invalid parameters
- `401` — Authentication failed - invalid API key
- `403` — Permission denied - API key lacks voice/TTS access

---

[API](https://skmtc.net/casemark/apis/case-dev-api.md) · [All operations](https://skmtc.net/casemark/apis/case-dev-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/casemark/case-dev-api/revisions/5b7e64e6d6f9/schema)