- Category: artificial intelligence
- Auth: API_KEY
- Composio-managed OAuth available? N/A
- Tools: 6
- Triggers: 0
- Slug:
INWORLD_AI - Version: 20261101_00
Tools
Create Embeddings
Create Embeddings
Slug:
INWORLD_AI_CREATE_EMBEDDINGSGenerate one complete embedding vector per input text with an Inworld-hosted embedding model. Batches can produce large responses.Input Parameters
Texts to embed, in output order. A call accepts 1-16 texts; each returned vector can be large.
Embedding service provider identifier. Use SERVICE_PROVIDER_INWORLD with the verified default model.
Output
Get Voice Preview
Get Voice Preview
List Models
List Models
List Voices
List Voices
Slug:
INWORLD_AI_LIST_VOICESReturn one page of voices available for preview or speech synthesis, with optional filtering, language selection, and sorting. The filter and languages parameters are mutually exclusive.Input Parameters
Optional AIP-160 filter, for example source = “IVC” for workspace-owned voices or source = “SYSTEM” for system voices. Cannot be combined with languages.
Output
Synthesize Speech
Synthesize Speech
Slug:
INWORLD_AI_SYNTHESIZE_SPEECHSynthesize short text with an Inworld voice and return the complete audio as a downloadable file. Long text can exceed tool payload limits; prefer short text and compressed MP3 output.Input Parameters
Text to speak (1-2000 characters). Prefer short text because generated base64 audio can exceed Composio/runtime payload limits.
Output audio encoding. MP3 is recommended to minimize transport size.
Whether to enable the provider’s generation enhancement when supported by the selected model.
Text-normalization mode. ON expands values such as numbers and abbreviations, OFF reads text as written, and APPLY_TEXT_NORMALIZATION_UNSPECIFIED lets Inworld decide.
Output
Transcribe Audio
Transcribe Audio
Slug:
INWORLD_AI_TRANSCRIBE_AUDIOSynchronously transcribe a short audio file and return the transcript, with word timestamps and usage when available. Prefer compressed input to limit base64 payload growth.Input Parameters
Synchronous STT model ID. The default was live-verified; groq/whisper-large-v3 is also supported for synchronous use.
Short audio file to transcribe. Prefer compressed MP3 and avoid large files because the API embeds audio as base64 JSON.
Encoding of audio_file; it must match the uploaded audio bytes. Use AUTO_DETECT for self-describing formats when the encoding is unknown.