API Reference - Lazybird Docs

Overview

The Lazybird Speech API lets you list available voices and generate MP3 speech from text or SSML.

Base URL:

Text

1https://api.lazybird.app/v1

Authentication

Create an API key from your Lazybird Studio settings, then send it with each request.

Preferred header:

HTTP

1X-API-Key: YOUR_API_KEY

You can also pass the key as an api_key query parameter when a tool cannot set headers:

Text

1https://api.lazybird.app/v1/voices?api_key=YOUR_API_KEY

Keep API keys private. Do not expose them in browser code, mobile apps, public repositories, or client-side logs.

Agent skill

When you are using an AI coding agent, install the official Lazybird API skill so the agent has the current API shape, examples, and integration gotchas available in context.

Install the Lazybird API skill

1npx skills add lazybirdai/skills --agent codex --skill lazybird-api

Quickstart

Generate speech with a known voice ID:

Generate speech

1curl -X POST "https://api.lazybird.app/v1/generate-speech" \2  -H "X-API-Key: $LAZYBIRD_API_KEY" \3  -H "Content-Type: application/json" \4  --output speech.mp3 \5  --data '{6    "voiceId": "msa.en-US.SerenaMultilingual",7    "text": "My name is Serena and I am a voice from Lazybird."8  }'

The response is an MP3 audio file. Save the response body to a file instead of trying to display it as JSON.

Check service status

HTTP

1GET /status

Returns the current API health.

Example:

Terminal

1curl "https://api.lazybird.app/v1/status"

Response:

JSON

1{2  "status": "ok"3}

List voices

HTTP

1GET /voices

Returns voices that can be used with generate-speech.

Example:

Terminal

1curl "https://api.lazybird.app/v1/voices" \2  -H "X-API-Key: $LAZYBIRD_API_KEY"

Response:

JSON

1[2  {3    "id": "msa.en-US.Jenny",4    "displayName": "Jenny",5    "language": "English (United States)",6    "gender": "Female",7    "previewText": "Hi, I am Jenny.",8    "avatar": "https://example.com/avatar.jpg"9  }10]

Use the id value as voiceId when generating speech.

Generate speech

HTTP

1POST /generate-speech

Generates speech with the selected voice and returns an MP3 audio file.

Headers:

Header	Required	Value
`X-API-Key`	Yes	Your Lazybird API key
`Content-Type`	Yes	`application/json`

Body:

Field	Type	Required	Description
`voiceId`	string	Yes	Voice ID from `/voices`
`text`	string	No	Plain text to convert to speech
`ssml`	string	No	SSML content. Use this instead of `text` when you need pauses or speech markup.
`settings`	object	No	Optional voice settings for this generation

Provide either text or ssml.

Plain text example

Terminal

1curl -X POST "https://api.lazybird.app/v1/generate-speech" \2  -H "X-API-Key: $LAZYBIRD_API_KEY" \3  -H "Content-Type: application/json" \4  --output speech.mp3 \5  --data '{6    "voiceId": "msa.en-US.SerenaMultilingual",7    "text": "My name is Serena and I am a voice from Lazybird."8  }'

SSML example

Terminal

1curl -X POST "https://api.lazybird.app/v1/generate-speech" \2  -H "X-API-Key: $LAZYBIRD_API_KEY" \3  -H "Content-Type: application/json" \4  --output speech.mp3 \5  --data '{6    "voiceId": "msa.en-US.SerenaMultilingual",7    "ssml": "<speak>My name is Serena <break time=\"1s\"/> and I am a voice from Lazybird.</speak>"8  }'

Voice settings example

All settings fields are optional.

JSON

1{2  "voiceId": "msa.en-US.SerenaMultilingual",3  "text": "This line is slower and slightly higher pitched.",4  "settings": {5    "style": "sad",6    "speed": 0.7,7    "pitch": 1.2,8    "volume": 1,9    "styleIntensity": 110  }11}

Settings:

Field	Type	Description
`style`	string	Speaking style or tone, when supported by the selected voice
`speed`	number	Speech speed. `1` is normal speed.
`pitch`	number	Voice pitch. `1` is the default pitch.
`volume`	number	Output volume. `1` is the default volume.
`styleIntensity`	number	Strength of the selected speaking style

Responses

Successful generate-speech requests return an MP3 file.

HTTP

1HTTP/1.1 200 OK2Content-Type: audio/mpeg

If a request fails, check that your API key is valid, the voiceId exists, and the request includes either text or ssml.

Testing tips

Make API requests from a server environment, not browser code.
Start by calling /voices and copying a voice ID from the response.
Save generate-speech responses with --output speech.mp3.
Keep SSML valid XML. Escape quotation marks correctly when sending SSML inside JSON.