impulse

TTS 1

Frontier labSpeechRetiring 6 Jan 2027
API id tts-1
Azure OpenAI retires it on 15 Dec 2026 (in 26 days); OpenAI (except 1106) on 6 Jan 2027. 1 host keeps serving it.
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
3 listings
Released
-
date not published

Where to run it

2 hosts serve TTS 1. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
tts-1
-
Retires 6 Jan 2027
tts-1
-
Retires 15 Dec 2026
Show 1 more listings: regions, snapshots and variants
OpenAI
1106
tts-1-1106
-

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 OpenAI models

Other frontier labs

Open-weight picks

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="tts-1", input="Hello")
print(response.output_text)

Quick answers

Which APIs offer TTS 1?

TTS 1 runs on 2 APIs: OpenAI and Azure OpenAI.

Is TTS 1 being retired?

Azure OpenAI retires it on 15 Dec 2026; OpenAI (except 1106) on 6 Jan 2027. 1 host keeps serving it.

What is TTS 1's API model id?

Use tts-1 with OpenAI.

Sources

Raw catalog entry for tts-1 on OpenAI
{
  "deprecation_date": "2027-01-06",
  "deprecation_source": "https://developers.openai.com/api/docs/deprecations",
  "successor_model": "gpt-realtime-2.1-mini",
  "input_cost_per_character": 0.000015,
  "litellm_provider": "openai",
  "mode": "audio_speech",
  "source": "https://developers.openai.com/api/docs/pricing",
  "supported_endpoints": [
    "/v1/audio/speech"
  ]
}