TTS‑1.5‑Mini is Inworld’s ultra‑fast, most cost‑efficient TTS model within the TTS‑1.5 lineup, tuned for near‑instant audio turnaround rather than studio‑demo polish. It targets applications such as voice‑first chatbots, interactive avatars, and real‑time games where fast turn‑taking and low time‑to‑first‑audio
Despite its compact footprint, TTS‑1.5‑Mini API delivers high‑quality, expressive speech suitable for core customer‑facing interactions and immersive experiences. It supports adjustable speaking rate and naturally flowing prosody, giving developers control over rhythm and pacing without sacrificing smoothness.
TTS‑1.5‑Mini covers the same 15 languages as TTS‑1.5‑Max, simplifying global rollout with a single, optimized low‑latency model. It also supports instant voice cloning, allowing teams to create and reuse recognizable persona voices from short reference clips over most supported languages.
Inworld TTS-1.5-Mini excels in speed tests, hitting under 120ms P90 latency, making it 4x faster than prior generations for production workloads. It ranks #1 in quality among efficient models while maintaining top stability for high-volume use.
Deploy TTS-1.5-Mini in scenarios demanding rapid audio generation, such as interactive chatbots, virtual assistants, and game dialogue systems. It's perfect for high-volume production, prototyping voiceovers, content accessibility tools, and multilingual apps where budget and speed matter most.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Inworld TTS 1.5 Mini is documented for conversational AI agents, where low latency helps voice assistants respond naturally without awkward pauses. It is also documented for real-time translation and dubbing, where speech synthesis needs to keep pace with live speakers. Another stated use case is interactive entertainment, including AI companions and narrative experiences that require expressive, real-time character speech. It is also documented for accessibility applications such as screen readers, navigation aids, and assistive technologies.
import requests r = requests.post( "https://api.aimlapi.com/v1/tts", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "inworld/tts-1-5-mini", "text": "Hello from AI/ML API", "voice": "alloy" }, ) print(r.json()["audio"]) # URL to the generated audio
const r = await fetch("https://api.aimlapi.com/v1/tts", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "inworld/tts-1-5-mini", "text": "Hello from AI/ML API", "voice": "alloy" }), }); const { audio } = await r.json(); console.log(audio); // URL to the generated audio
curl -X POST https://api.aimlapi.com/v1/tts \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"inworld/tts-1-5-mini","text":"Hello from AI/ML API","voice":"alloy"}' # the JSON response contains "audio" — a URL to the generated speech
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Inworld TTS-1.5-Mini This page | Speech synthesis | |||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis | ||||
| Speech synthesis |
Inworld TTS-1.5-Mini takes text as input and returns audio.
Inworld TTS-1.5-Mini is priced at $5.25 / 1M tokens.
Inworld TTS-1.5-Mini is billed per generation — a fixed charge per output rather than by prompt length.
Inworld TTS-1.5-Mini was built by Inworld AI.
Send a request to https://api.aimlapi.com/v1/tts with inworld/tts-1-5-mini as the model id.
Yes. Inworld TTS-1.5-Mini is served through AI/ML API, so the same key and endpoint format used for other models applies.
Its model ID is inworld/tts-1-5-mini.
It is a text-to-speech model optimized for low-latency, real-time and high-throughput use while maintaining high audio quality.
