v4

OpenAPI 3.1.02026-07-313621,3961.8 MB

text-to-voice

[Deprecated] Generate A Voice Preview From Description

Deprecated. Use POST /v1/text-to-voice/design instead. Generate a custom voice based on voice description. This method returns a list of voice previews. Each preview has a generated_voice_id and a sample of the voice as base64 encoded mp3 audio. To create the voice use POST /v1/text-to-voice with the chosen generated_voice_id.

post/v1/text-to-voice/create-previews

Query parameters

output_format'mp3_22050_32' | 'mp3_24000_48' | 'mp3_44100_32' | 'mp3_44100_64' | 'mp3_44100_96' | 'mp3_44100_128' | 'mp3_44100_192' | 'pcm_8000' | 'pcm_16000' | 'pcm_22050' | 'pcm_24000' | 'pcm_32000' | 'pcm_44100' | 'pcm_48000' | 'ulaw_8000' | 'alaw_8000' | 'opus_48000_32' | 'opus_48000_64' | 'opus_48000_96' | 'opus_48000_128' | 'opus_48000_192'

Output format of the generated audio. Formatted as codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires you to be subscribed to Pro tier or above. Note that the μ-law format (sometimes written mu-law, often approximated as u-law) is commonly used for Twilio audio inputs.

Headers

xi-api-keystring nullable

Your API key. This is required by most endpoints to access our API programmatically. You can view your xi-api-key using the 'Profile' tab on the website.

Request body

voice_descriptionstring required

Description to use for the created voice.

textstring nullable

Text to generate, text length has to be between 100 and 1000.

auto_generate_textboolean

Whether to automatically generate a text suitable for the voice description.

loudnessnumber

Controls the volume level of the generated voice. -1 is quietest, 1 is loudest, 0 corresponds to roughly -24 LUFS.

qualitynumber

Higher quality results in better voice output but less variety.

seedinteger nullable

Random number that controls the voice generation. Same seed with same inputs produces same voice.

guidance_scalenumber

Controls how closely the AI follows the prompt. Lower numbers give the AI more freedom to be creative, while higher numbers force it to stick more to the prompt. High numbers can cause voice to sound artificial or robotic. We recommend to use longer, more detailed prompts at lower Guidance Scale.

should_enhanceboolean

Whether to enhance the voice description using AI to add more detail and improve voice generation quality. When enabled, the system will automatically expand simple prompts into more detailed voice descriptions. Defaults to False

Example request

{
  "voice_description": "A sassy squeaky mouse",
  "text": "Every act of kindness, no matter how small, carries value and can make a difference, as no gesture of goodwill is ever wasted.",
  "loudness": 0.5,
  "quality": 0.9,
  "seed": 11,
  "guidance_scale": 5,
  "should_enhance": true
}

Response

Successful Response

textstring required

The text used to preview the voices.