Skip to main content
Inworld’s Speech-to-Text (STT) API provides a unified integration point for industry-leading transcription providers. You get consistent authentication, request formatting, and response handling across providers — without managing multiple SDKs or credentials. The API supports both synchronous transcription for complete audio files and real-time bidirectional streaming over WebSocket for live audio.

Developer Quickstart

Make your first STT API call and get a transcript.

API Reference

View the complete API specification.

Code Examples

Browse ready-to-use GitHub samples for sync and real-time STT.

​
Supported Providers

​
Inworld (first-party) — Experimental

Model IDEndpointsBest for
inworld/inworld-stt-1Sync API + WebSocketVoice agents and character-driven apps that benefit from transcription plus Voice Profile (age, pitch, emotion, vocal style, accent) and configurable turn-taking
The Inworld first-party model is currently Experimental. Features and pricing are subject to change.

​
Groq

Model IDEndpointsBest for
groq/whisper-large-v3Sync API onlyGeneral-purpose transcription for recorded audio

​
AssemblyAI

Model IDEndpointsBest for
assemblyai/universal-streaming-multilingualWebSocket onlyMultilingual streaming (English, Spanish, French, German, Italian, Portuguese)
assemblyai/universal-streaming-englishWebSocket onlyEnglish-optimized streaming
assemblyai/u3-rt-proWebSocket onlyHigh-accuracy, sub-300ms latency, multilingual streaming (English, Spanish, French, German, Italian, Portuguese)
assemblyai/whisper-rtWebSocket onlyReal-time Whisper transcription
AssemblyAI models currently support the WebSocket streaming endpoint only. Sync HTTP support is coming soon.
For pricing details, see Billing or inworld.ai/pricing.

​
Model comparison

Featureinworld/inworld-stt-1groq/whisper-large-v3assemblyai/universal-streaming-multilingualassemblyai/universal-streaming-englishassemblyai/u3-rt-proassemblyai/whisper-rt
Pricing$0.28/hour$0.111/hour$0.15/hour$0.15/hour$0.45/hour$0.30/hour
EndpointSync API + WebSocketSync API onlyWebSocket onlyWebSocket onlyWebSocket onlyWebSocket only
Real-time streaming
Best forVoice agents with Voice Profile and configurable turn-takingGeneral-purpose transcription for recorded audioMultilingual streaming (English, Spanish, French, German, Italian, Portuguese)English-optimized streamingHigh-accuracy, sub-300ms multilingual streaming (English, Spanish, French, German, Italian, Portuguese)Real-time Whisper transcription
LanguagesEnglish100+ (Whisper)6 languagesEnglish6 languages100+ (Whisper)

​
Supported Audio Formats

FormatSync APIWebSocket Streaming
LINEAR16 (PCM)
MP3
OGG_OPUS
FLAC
AUTO_DETECT
Recommended defaults: 16,000 Hz sample rate, 16-bit depth, mono. For container formats (MP3, FLAC, OGG_OPUS, WAV), sampleRateHertz is optional — the API auto-detects it from the file header.

​
Endpoints

EndpointMethodDescription
/stt/v1/transcribePOSTSend complete audio, receive full transcript
/stt/v1/transcribe:streamBidirectionalWebSocketStream audio in real time, receive transcription chunks as they become available

​
Supported Languages

Language support depends on the STT provider. See Model comparison above for more details. Use language when you want to force recognition for a known language. Omit language to allow auto-detection when supported.

​
Error Handling

Responses use a consistent error shape. Providers may add extra codes. Authentication error 
{
  "error": {
    "code": "AUTHENTICATION_FAILED",
    "message": "Invalid API key. Expected Base64-encoded credentials."
  }
}
Rate limit 
{
  "error": {
    "code": "RATE_LIMIT_EXCEEDED",
    "message": "Maximum concurrent requests exceeded. Retry after 5 seconds."
  }
}
Common codes
CodeDescription
AUTHENTICATION_FAILEDInvalid or missing API key
RATE_LIMIT_EXCEEDEDToo many concurrent requests
INVALID_AUDIO_FORMATEncoding does not match the declared format
UNSUPPORTED_LANGUAGELanguage not supported by the selected provider

​
Best Practices

  • Model choice — Use inworld/inworld-stt-1 when you want Voice Profile or Inworld-optimized turn-taking; use Groq/AssemblyAI for specific latency/accuracy needs.
  • Audio — Use MP3/OGG_OPUS for file uploads to reduce size; use LINEAR16 for streaming (required) and when you need highest quality.
  • Streaming — For Inworld model with manual turn-taking, send EndTurn at each turn boundary and CloseStream when done.
  • Voice Profile — Set inworldConfig.voiceProfileThreshold (e.g. 0.5) to filter low-confidence labels.
  • Test with sample audio and your target language before production.

​
Troubleshooting

IssueWhat to check
No transcriptAPI key, audio encoding matches request, valid audio file
AUTHENTICATION_FAILEDINWORLD_API_KEY set correctly and not expired in Portal
INVALID_AUDIO_FORMATaudioEncoding matches the actual format (LINEAR16 for raw PCM, MP3 for MP3, etc.)
Poor qualityTry a higher-accuracy model; use ≥16 kHz, clear speech
Large file failuresSplit or compress (e.g. MP3/OGG_OPUS); respect upload size limits
No Voice ProfileResponse may omit it if not available for the selected model or request
For more help, see the Inworld Discord community.