Skip to main content
MindStudio
Pricing
BlogAbout
My Workspace
Text to Speech Model

Inworld TTS-2

Text to Speech by Inworld

PublisherInworld
TypeText to Speech
Context Window2,000 tokens
Released2026
Price$35 / 1M characters
ProviderDeepInfra
LATESTMULTILINGUALLOW LATENCY

Ready to build with Inworld TTS-2?

Get Started Free

Parameters & options

VoiceSelect

Preset voice; every voice speaks every language. Steer the delivery in the text itself, e.g. "[be happy and upbeat] Hello!".

Default: Ashley
AbbyAlainAlexAminaAnjaliArjunAshleyAsukaAveryBiancaBlakeBrandonBrianCallumCarterCedricCelesteChloeClaireCliveConradCraigDamonDarleneDeborahDennisDerekDiegoDmitryDominusEdwardElenaElizabethElliotErikEthanEvanEvelynGarethGianniGrahamGrantHadesHamishHanaHankHeitorHyunwooJakeJamesJasonJessicaJingJohannaJonahJosefJuliaKatrienKaylaKelseyLaurenLennartLeviLiamLoreLorettaLucianLunaLupitaMalcolmManojMarcusMarkMarleneMathieuMiaMiguelMinjiMirandaMortimerNadiaNaomiNateNikolaiNourOliverOliviaOmarOrenOriettaPippaPixiePriyaRafaelRileyRiyaRonaldRupertSaanviSarahSatoshiSebastianSeleneSeojunSerenaShaunSimonSnikSvetlanaSzymonTessaTheodoreTimothyTrevorTristanTylerVeronicaVictorVictoriaVinnyWendyWojciechXiaoyinXinyiYaelYichenYoona
TemperatureNumber

How much the delivery varies from one reading to the next. Higher is livelier, lower steadier.

Range: 0–2 (step 0.05)
Output FormatSelect
Default: mp3
MP3WAVFLACOpus

Start building with Inworld TTS-2

No API keys required. Create AI-powered workflows with Inworld TTS-2 in minutes — free.