Can Lyro generate speech with the Groq PlayAI voices?

No. List TTS Voices returns the PlayAI voice options, but this toolkit exposes no synthesis action, so nothing here turns text into audio. That voice list is also maintained manually rather than fetched live, which makes it a reference rather than a guarantee of availability.

Which audio files work, and what language comes back?

Create Audio Transcription accepts mp3, mp4, wav, and webm, and returns text in the language that was spoken. Create Audio Translation takes the same recording and returns English - it is one-way, so there is no route to a third language.

Why does Lyro list the models before running a request?

Because model IDs get retired and a stale one makes Create Chat Completion and Retrieve Model fail outright. List Models returns the current IDs, and the metadata behind them is explicitly not safe to cache, so it is re-read rather than remembered.

Whose rate limits apply to these calls?

The limits on the GroqCloud account you connect. High request volume, especially combined with frequent List Models polling, returns HTTP 429 rate_limit_exceeded, so calls are spaced with backoff instead of being retried immediately.

Groqcloud MCP integration

Generates chat completions, transcribes and translates audio recordings, and checks the live model catalogue before every request.

Connect Groqcloud See all integrations

7actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

Create chat completion
Lyro generates natural language responses to customer messages using advanced AI models. Support teams respond faster without waiting for manual composition.
Create audio transcription
Lyro converts customer voice messages into text automatically. Support agents read and respond to voice inquiries without playing back audio repeatedly.
Retrieve model
Lyro fetches detailed specifications and performance data for AI models. Engineers verify model capabilities before deploying solutions to production.

See all 7 actions

How businesses use Groqcloud + Lyro

Each card is one request a support team gets, and the Groqcloud actions Lyro runs to close it.

Generate a reply from the conversation so far
Lyro sends the prior messages to a Groq-hosted model and gets the next reply back, or uses the simplified Create Response endpoint when a single prompt is all the context needed.
Create Chat CompletionCreate ResponseList Models
Turn a recording into text in its own language
Audio in mp3, mp4, wav, or webm comes back as a transcript in the language it was spoken, ready to summarise or file without a manual listening pass.
Create Audio TranscriptionCreate Chat CompletionList Models
Get an English transcript of a non-English call
A recording in another language is translated straight through to English text in one step, so a team that does not speak it can still read what was said.
Create Audio TranslationCreate Audio TranscriptionCreate Chat Completion
Route requests at models that still exist
Model IDs on GroqCloud are retired over time and a stale one fails the call, so Lyro pulls the current list and the metadata behind a chosen model instead of trusting a hard-coded name.
List ModelsRetrieve ModelList TTS Voices

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Groqcloud actions it has and picks the ones a request needs.

01
Connect Groqcloud
Authorize the Groqcloud account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Groqcloud actions that close it and chains as many as the request needs.
03
Watch it work
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started free

Groqcloud · Lyro

Everything else about Groqcloud

Setup, permissions, and the limits of what Lyro can do inside Groqcloud.

No. List TTS Voices returns the PlayAI voice options, but this toolkit exposes no synthesis action, so nothing here turns text into audio. That voice list is also maintained manually rather than fetched live, which makes it a reference rather than a guarantee of availability.

Every action available in Groqcloud

All 7 actions your agent can call on Groqcloud, straight from the live MCP connection.

Create audio transcription
Transcribe audio into text in the same language as the audio.
Create response
Create a model response for the given input.
Create audio translation
Translate an audio file into English text.
Create chat completion
Generate a chat-based completion for a conversation.
Retrieve model
Retrieve detailed information about a specific model.
List models
List all available models and their metadata.
List tts voices
Retrieve available TTS voices for Groq PlayAI models.