> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ekly.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Speech and music

> One endpoint, two kinds of model.

`POST /v1/audio` serves both speech and music; the `model` decides which, and the fields you send
differ.

## Speech

Send `text` and a `voice_name` (or a voice id from your workspace). ElevenLabs Multilingual v2 and
Turbo v2.5 cover most languages; v3 understands expressive cues in the text. Long scripts can be
split into `segments` with different voices for dialogue.

## Music

Send a `prompt` describing style, mood and instrumentation. Lyria takes tag-style prompts with
energy and tempo; ElevenLabs Music (`music_v1` / `music_v2`) takes free text, an instrumental
toggle, and lyrics with `[Verse]` / `[Chorus]` markers.

Pricing is per character for speech and per generation for music; estimate with `character_count`
for speech. Voice-specific tips: the [ElevenLabs prompting guide](https://ekly.ai/guides/elevenlabs-prompting).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.