STT
STT Playground
Record live or upload audio to transcribe with Inworld STT
Try Inworld STT in the STT Playground before writing code. Start by transcribing your audio, then tune language hints and custom vocabulary. Optionally explore Voice Profile to analyze how the speaker sounds.
Get Started
Go to Inworld Portal
In Portal, select Speech-to-Text from the left-hand side panel.
Choose a model
Open Model in the right-hand panel to select inworld/inworld-stt-1. See Supported models for its endpoints and language coverage.
Record or upload audio
For your first transcription, leave the Voice Profile switch off. The playground remembers your choice in this browser, so check the switch if you have used it before.
Press the mic button to transcribe live from your microphone, or use the upload button to transcribe an audio file. The status bar shows Ready when the playground can accept audio and Listening… while recording.
Advanced Features
To control transcription, try these settings:
-
Language hint — The Language dropdown defaults to Auto-detect, which recognizes the spoken language automatically. Select a specific language to give the model a hint when you know the audio's language in advance — this generally improves accuracy, especially for short utterances. See Language Support for how hints behave.
-
Custom vocabulary — To bias recognition toward names, jargon, or acronyms, enter them in Custom vocabulary and press Enter. Terms appear as chips, with the active term count below the input. This is a soft bias rather than a hard keyword lock — test it on the terms the baseline actually misses. Up to 100 terms, using letters, digits, spaces, and
. , ' ( ) : ! ? ; -only — a term with any other character (such as&,_, or a curly quote) makes the request fail. The equivalent API field isprompts. -
Speaker diarization — Turn on the Speaker diarization toggle to label who said what in multi-speaker audio. The transcript prefixes each turn with a speaker label (
[Speaker 1],[Speaker 2], …). The equivalent API fields areenableSpeakerDiarizationtogether withincludeWordTimestamps— speaker labels are returned on the word timestamps, so both must be enabled. See Speaker Diarization for how labels are assigned and its current experimental status oninworld/inworld-stt-1. -
Voice Profile — Analyze Age, Accent, Voice Pitch, Vocal Style, and Emotion alongside the transcript, each with a confidence score. Use these signals for an agent's responses or conversation analytics.
Voice Profile is an optional paid add-on, billed separately from transcription. See STT billing and pricing.
After your recording or upload finishes processing, turn on the Voice Profile switch in the right-hand panel. Record again or upload the same audio to compare the transcript with the additional speaker signals. Treat the results as estimates; some may be missing if the audio does not support a confident classification.
To return to transcription only, turn the switch off before your next recording or upload. Your choice is remembered in this browser. See Voice Profiles for the category reference and ways to use the signals in your application.
From Playground to Code
Review the Voice Profile switch before exporting code. Turn it off for transcription only, or leave it on to include the paid add-on in your API requests.
Click Integrate at the top of the playground to generate an API request matching your current playground configuration: model, language hint, vocabulary, speaker diarization, and Voice Profile settings. When Voice Profile is enabled, the generated request includes voiceProfileConfig with enableVoiceProfile: true. Remove that block or set it to false if you do not want the add-on in your integration.
Next Steps
Ready to build? Here's where to go next.