Novita's Inworld TTS 2 Targets Voice Apps

// 58m agoPRODUCT UPDATE

Novita's Inworld TTS 2 Targets Voice Apps

Novita exposes Inworld’s expressive Realtime TTS-2 model through a synchronous API with voice cloning, delivery controls, multiple audio formats, and word- or character-level timestamps. The integration is billed per character and documented for narration, character voices, captions, and avatar audio.

// ANALYSIS

This is a useful distribution update, not a new model launch: Novita makes Inworld’s existing TTS-2 capabilities easier to consume through another inference platform.

–`STABLE`, `BALANCED`, and `CREATIVE` delivery modes give developers more meaningful control than temperature, which TTS-2 ignores.
–Short-sample voice cloning lowers onboarding friction, though shared cloned voices per API key create multi-tenant ownership concerns.
–Word and character timestamps plus broad encoding support make the API practical for captions, karaoke highlighting, and lip-sync pipelines.
–The synchronous 2,000-code-unit limit and base64 response format are less suitable for long-form narration or streaming agents.
–Inworld launched TTS-2 in August 2026, so Novita’s value here is platform access and integration rather than model novelty. ([Inworld](https://inworld.ai/blog/realtime-tts-2), [Inworld TTS docs](https://docs.inworld.ai/api-reference/ttsAPI/texttospeech/synthesize-speech))

// TAGS

inworld-tts-2novita-aittsspeechvoice-agentapiinferencecloud

DISCOVERED

58m ago

2026-11-10

PUBLISHED

2h ago

2026-11-10

RELEVANCE

8/ 10

AUTHOR

inworld

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH58m ago

Meta's AutoRefine Calibrates Code Judges

Meta’s AutoRefine paper presents a prompt-rewriting loop that uses noisy workflow outcomes—tests, merges, and abandons—to recalibrate LLM code judges, while abstaining when outcomes cannot be explained by the judge’s inputs. On held-out diffs from a deployed coding agent, agreement rose from Scott’s π 0.16 to 0.51. ([paper](https://arxiv.org/abs/2611.09291))

INFRA1h ago

Browser Use Cloud Clears CAPTCHA Bottleneck

Browser Use’s stealth cloud browser combines hardened Chromium, residential proxies, and automatic CAPTCHA solving for AI agents. The company reports 90.5% successful visits across 100 bot-protected sites in its own benchmark.

RESEARCH1h ago

Sycophantic AI Warnings Miss Their Mark

A preregistered study of 2,610 people found that warnings reduced perceived AI objectivity and trust, but did not reliably reduce users’ belief that they were right or their willingness to repair interpersonal conflicts. [Read the paper](https://arxiv.org/abs/2606.21317)