# Lero Docs

> Lero turns text into speech in Brazilian Portuguese, with a regional accent. The Lero API takes the text and the voice and returns an MP3, with the voices rio (Rio de Janeiro), sp (São Paulo) and niteroi (Niterói). Speech-to-Text transcribes Brazilian Portuguese audio, with timestamps for each sentence and ready subtitles. The Conversational Agent is a live voice agent over WebRTC, with your system prompt and knowledge base. The Lero MCP puts this voice inside Claude Code, Codex, Cursor and Claude Desktop.

Base URL: https://app.lero.studio/api/v1. Authentication: `Authorization: Bearer lero_...`. TTS: 1 credit per character. STT: 150 credits per minute of audio. Portuguese version: https://lero.studio/docs/llms.txt

## Docs

- [API Reference](https://lero.studio/docs/en): direct integration, quickstart, key, errors, limits and the routes (TTS, STT and Conversational Agent).
- [Build with AI](https://lero.studio/docs/en/ai): the MCP, the integration prompt, docs for agents and the skill.
- [llms-full.txt](https://lero.studio/docs/en/llms-full.txt): all the docs in one Markdown file.
- [openapi.json](https://lero.studio/docs/en/openapi.json): OpenAPI 3.1 contract of the routes.
- [prompt.md](https://lero.studio/docs/en/prompt.md): prompt to paste into your coding agent.
- [skill.md](https://lero.studio/docs/en/skill.md): the `lero-api` Agent Skill for coding agents.
- [MCP](https://lero.studio/docs/en/ai#mcp): stdio MCP server, `npx -y lero-mcp`, with the key in `LERO_API_KEY`.

## Start

- [Direct integration](https://lero.studio/docs/en#integracao)
- [Quickstart](https://lero.studio/docs/en#inicio)
- [Key](https://lero.studio/docs/en#chave)
- [Errors](https://lero.studio/docs/en#erros)
- [Credits and limits](https://lero.studio/docs/en#limites)

## Routes

- [Generate speech](https://lero.studio/docs/en#fala): `POST /v1/tts`. Turns the text into speech and returns the MP3 (`audio/mpeg`). Costs 1 credit per character of the text, charged before generating and refunded if generation fails.
- [List voices](https://lero.studio/docs/en#vozes): `GET /v1/voices`. The list of voices, with id and name. Free.
- [Transcribe audio](https://lero.studio/docs/en#transcricao): `POST /v1/stt`. Turns audio into text, in spoken Brazilian Portuguese: slang, acronyms, numbers and names come out right. Returns the text with paragraphs and the sentences with start and end times; on request, the time of each word or ready subtitles (SRT or VTT).
- [Credits left](https://lero.studio/docs/en#saldo): `GET /v1/balance`. The account credits right now, with this month's allowance, and the plan. Free.
- [List versions and LLMs](https://lero.studio/docs/en#agentes): `GET /v1/agents`. Conversational Agent discovery: the agent versions your key can use, the LLMs, the voices and the recommended setup. Call it before opening a call: the list changes. Free.
- [Open a call (WebRTC)](https://lero.studio/docs/en#conversa): `POST /v1/agents/conversation`. Live call signaling: you send the SDP offer of your WebRTC client and get the SDP answer. After that, audio and the `chat` data channel flow peer-to-peer between your client and the agent (streaming STT, LLM and TTS, with barge-in and turn detection). Without `versao`, `llm` and `voz`, the recommended setup applies. With `instrucoes`, the agent becomes yours: the system prompt replaces the Lero persona. Step by step in [Conversational Agent: step by step](#agente-guia).

## More

- [Webhooks](https://lero.studio/docs/en#webhooks)
- [Conversational Agent: step by step](https://lero.studio/docs/en#agente-guia)
- [Examples](https://lero.studio/docs/en#exemplos)
- [Support](https://lero.studio/docs/en#suporte)