inworld-ai/realtime-tts-2
Realtime TTS 2.0 is a low-latency text-to-speech model with natural language steering, allowing you to control tone and emotion directly in the prompt (e.g., “[be happy and upbeat] Hello!”). It supports cross-lingual voices and multiple languages, enabling the same voice to speak consistently across different languages. This is an early access preview ahead of full launch, with ongoing improvements to voice quality and steering.
Try the model with a sample request using the same API shape shown in the reference page.
Text to convert to speech
Sample rate for the output audio (Default: 24000)
Whether to return word-level timestamps
Language hint (e.g. "AUTO" or a specific code like "EN_US"). Supported by realtime-tts-2; ignored by 1.5 models.. (Default: empty)
Temperature controls variability of the speech (Default: empty, 0 ≤ temperature ≤ 2)
Whether to stream the output.
Speaking rate of the speech (Default: 1, 0.5 ≤ speaking_rate ≤ 1.5)
Select the desired format for the speech output. Supported formats include mp3, opus, flac, wav, and pcm.
Preset voice name (Ashley, Diego, etc.) or a voice_id from /v1/voices/add for voice cloning.
The service tier used for processing the request. When set to 'priority', the request will be processed with higher priority (only applies to models that support it).
Adjust settings and run the demo to see the model output generated here in real-time.
