impulse

Lyria 002

Frontier labSpeech
API id lyria-002
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Where to run it

1 host serve Lyria 002. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
lyria-002
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Audio
Features
Audio output

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Google models

Other frontier labs

Open-weight picks

Call it

Using Vertex AI's API.

Python
from google import genai

client = genai.Client()  # reads GEMINI_API_KEY

response = client.models.generate_content(model="lyria-002", contents="Hello")
print(response.text)

Quick answers

Which APIs offer Lyria 002?

Lyria 002 runs on 1 API: Vertex AI.

Is Lyria 002 being retired?

No retirement date is scheduled for it on any API we track.

What is Lyria 002's API model id?

Use lyria-002 with Vertex AI.

Sources

Raw catalog entry for lyria-002 on Vertex AI
{
  "litellm_provider": "vertex_ai",
  "mode": "audio_speech",
  "output_cost_per_image": 0.06,
  "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing#lyria",
  "supported_audio_formats": [
    "wav"
  ],
  "supported_endpoints": [
    "/v1/audio/speech"
  ],
  "supported_modalities": [
    "text"
  ],
  "supported_output_modalities": [
    "audio"
  ],
  "supports_audio_output": true,
  "vertex_ai_audio_api": "lyria_predict"
}