Skip to main content
The Realtime 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.
Using AI to code? Paste https://docs.inworld.ai/llms.txt into your assistant so it knows every page on this site. Want live search? Add the MCP server.

​
Supported Providers

​
Inworld (first-party)

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
Supports 30 languages. See Language Support for the full list.

​
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.

​
Soniox

Model IDEndpointsBest for
soniox/stt-rt-v4WebSocket onlyHigh-accuracy real-time streaming with semantic end-of-turn detection and multilingual support
Soniox models currently support the WebSocket streaming endpoint only.
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-rtsoniox/stt-rt-v4
PricingSee pricingSee pricingSee pricingSee pricingSee pricingSee pricingSee pricing
EndpointSync API + WebSocketSync API onlyWebSocket 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 transcriptionHigh-accuracy real-time streaming with semantic end-of-turn detection and multilingual support
Languages30 languages (see list)100+ (Whisper)6 languagesEnglish6 languages100+ (Whisper)Multilingual

​
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.
Sync transcription accepts audio files up to ~16 MB. The actual duration depends on the encoding — for example, ~18 minutes of MP3 or ~8 minutes of 16 kHz 16-bit WAV. For larger files, split them into chunks or use the WebSocket streaming endpoint.
STT performs best with 16 kHz audio. Lower sample rates (such as 8 kHz telephony audio) contain fewer data points for the model to interpret, which reduces transcription accuracy. Upsampling low-sample-rate audio does not improve quality — it only interpolates between existing samples without adding new information.

​
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 Language Support for the full list of languages supported by the Inworld first-party model, and links to third-party provider language documentation.

​
Error Handling

Errors follow the standard gRPC status format. Authentication error 
{
  "code": 16,
  "message": "Unauthenticated: invalid or missing API key.",
  "details": []
}
Invalid request 
{
  "code": 3,
  "message": "Unsupported audio encoding.",
  "details": []
}
Common gRPC status codes
CodeNameDescription
3INVALID_ARGUMENTInvalid or missing request field (encoding, model ID, audio data)
8RESOURCE_EXHAUSTEDToo many concurrent requests (rate limit)
16UNAUTHENTICATEDInvalid or missing API key

​
Best Practices

  • Model choice — Use inworld/inworld-stt-1 when you want Voice Profile or Inworld-optimized turn-taking; use Groq/AssemblyAI/Soniox 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.
  • Speech events — Listen for speechStarted and speechStopped events in the streaming response to detect when a speaker begins and stops talking. Use these to build custom turn-taking logic or visualize voice activity.
  • Voice Profile — Set voiceProfileConfig.enableVoiceProfile to true and optionally adjust topN (default: 10) to control how many labels per category are returned.
  • Test with sample audio and your target language before production.

​
Troubleshooting

IssueWhat to check
No transcriptAPI key, audio encoding matches request, valid audio file
UNAUTHENTICATEDINWORLD_API_KEY set correctly and not expired in Portal
INVALID_ARGUMENTaudioEncoding matches the actual format (LINEAR16 for raw PCM, MP3 for MP3, etc.)
Poor qualityTry a higher-accuracy model; use 16 kHz sample rate (8 kHz telephony audio has fewer data points and will produce lower-quality results); ensure clear speech
Large file failuresSplit or compress (e.g. MP3/OGG_OPUS); respect upload size limits
No Voice ProfileEnsure voiceProfileConfig.enableVoiceProfile is set to true in your request; response may also omit it if the selected model does not support it
For more help, see the Inworld Discord community.