impulse

Realtime TTS 1.5 Max

Speech
API id realtime-tts-1.5-max
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 Realtime TTS 1.5 Max. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
ReplicateInference
realtime-tts-1.5-max
-

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

Similar models

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

Smaller Independent models

No similar Independent model keeps its key capabilities.

Other frontier labs

Open-weight picks

Call it

Using Replicate's API.

Python
from litellm import completion

response = completion(
    model="replicate/realtime-tts-1.5-max",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Realtime TTS 1.5 Max?

Realtime TTS 1.5 Max runs on 1 API: Replicate.

Is Realtime TTS 1.5 Max being retired?

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

What is Realtime TTS 1.5 Max's API model id?

Use realtime-tts-1.5-max with Replicate.

Sources

Raw catalog entry for realtime-tts-1.5-max on Replicate
{
  "input_cost_per_character": 0.000035,
  "litellm_provider": "replicate",
  "mode": "audio_speech",
  "source": "https://replicate.com/inworld/realtime-tts-1.5-max"
}