Inworld TTS-1.5 latency

TTS-1.5 Max delivers under 250ms time-to-first-audio (P90), while TTS-1.5 Mini goes under 130ms both 4x faster than previous generations. For most applications, Max offers the best balance of speed and quality.

Inworld TTS-1.5 supported languages

Inworld TTS-1.5 supports 15 languages including English, Hindi, French, German, and Spanish, with 65+ expressive voices. Pricing starts at $5–10 per million characters 25x more affordable than comparable alternatives.

Example inputhover

apply_text_normalization: "APPLY_TEXT_NORMALIZATION_UNSPECIFIED"
audio_encoding: "MP3"
bit_rate: 40000
model_id: "inworld-tts-1.5-mini"
text: "Hey everyone, welcome to Eachlabs AI! Eachlabs is an advanced AI platform that offers powerful tools for text, image, and voice generation. It’s built to help creators, developers, and businesses produce high-quality content quickly and easily. With a focus on realism, speed, and flexibility, Eachlabs supports a wide range of creative and commercial use cases, making AI more accessible and impactful for everyone."
voice_id: "Alex"
speaking_rate: 1
temperature: 1.1

Inworld TTS 1.5

Audio·Inworld·by Inworld

Inworld-TTS-1.5 is an advanced text-to-speech (TTS) model that converts written text into natural, expressive, and human-like speech. Designed for low latency and real-time performance, it supports high-quality voice output for applications such as voice assistants, games, interactive experiences, and content creation.

Try it now →

API reference

Runtime (p50): 1s
Estimated price: From $0.000005

Call the API

prediction.sh

curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "inworld-tts-1-5",
    "version": "0.0.1",
    "input": {
        "apply_text_normalization": "APPLY_TEXT_NORMALIZATION_UNSPECIFIED",
        "audio_encoding": "MP3",
        "bit_rate": 40000,
        "model_id": "inworld-tts-1.5-mini",
        "text": "Hey everyone, welcome to Eachlabs AI! Eachlabs is an advanced AI platform that offers powerful tools for text, image, and voice generation. It’s built to help creators, developers, and businesses produce high-quality content quickly and easily. With a focus on realism, speed, and flexibility, Eachlabs supports a wide range of creative and commercial use cases, making AI more accessible and impactful for everyone.",
        "voice_id": "Alex",
        "speaking_rate": 1,
        "temperature": 1.1
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models

Mureka | Generate Remix AI model preview

Mureka | Generate RemixMureka

Mureka | Generate Soundtrack AI model preview

Mureka | Generate SoundtrackMureka

Minimax | Speech | 2.8 | Turbo AI model preview

Minimax | Speech | 2.8 | TurboMinimax

Minimax Music | V1.5Minimax

* FAQ

About Inworld TTS 1.5

01 / 03

What is Inworld TTS-1.5

Inworld TTS-1.5 is a real-time text-to-speech model ranked #1 on the Artificial Analysis TTS Leaderboard. It delivers 30% greater expressiveness and 40% fewer word errors than its predecessor, making it ideal for voice agents, interactive media, and accessibility applications.