Text-to-speech synthesis

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.

POST /voice/v1/speak

cURL

cURL

curl -X POST "https://api.case.dev/voice/v1/speak" \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "text": "<string>"
}'

200

"<string>"

Authorizations

Authorization · string · header · required

API key starting with sk_case_

Body

application/json

text · string · required

Text to convert to speech

Maximum string length: 5000

voice_id · string · default: EXAVITQu4vr4xnSDxMaL

ElevenLabs voice ID (defaults to Rachel - professional, clear)

model_id · enum<string> · default: eleven_multilingual_v2

ElevenLabs model ID

Available options: eleven_multilingual_v2, eleven_turbo_v2, eleven_monolingual_v1

output_format · enum<string> · default: mp3_44100_128

Audio output format

Available options: mp3_44100_128, mp3_44100_192, pcm_16000, pcm_22050, pcm_24000, pcm_44100

voice_settings · object

Voice customization settings

Show child attributes

language_code · string

Language code for multilingual models

Example:

"en"

optimize_streaming_latency · integer

Optimize for streaming latency (0-4)

Required range: 0 <= x <= 4

enable_logging · boolean · default: true

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 · default: true

Apply automatic text normalization

Response

200

audio/mpeg

Audio file generated successfully

The response is of type file.