Transcribe audio to text using leading STT providers through a single API.
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.
Voice agents and character-driven apps that benefit from transcription plus Voice Profile (age, pitch, emotion, vocal style, accent) and configurable turn-taking
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.
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.
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.
Language hint — If you know the audio’s language, set language (e.g. en, ja) for cleaner output; for inworld/inworld-stt-1 the hint also constrains the output script (see Language Support). Leave it empty to auto-detect or when speakers switch languages.
Custom vocabulary — Pass domain-specific terms (names, jargon, acronyms) in prompts to bias recognition toward them. It is a soft bias rather than a hard keyword lock, so test it on the cases where the baseline actually misses the term.
Test with sample audio and your target language before production.
API key, audio encoding matches request, valid audio file
UNAUTHENTICATED
INWORLD_API_KEY set correctly and not expired in Portal
INVALID_ARGUMENT
audioEncoding matches the actual format (LINEAR16 for raw PCM, MP3 for MP3, etc.)
Poor quality
Try 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 failures
Split or compress (e.g. MP3/OGG_OPUS); respect upload size limits
No Voice Profile
Ensure voiceProfileConfig.enableVoiceProfile is set to true in your request; response may also omit it if the selected model does not support it
