Realtime STT
Speech-to-text API (Inworld STT-1) that transcribes streaming or complete audio in 30+ languages with turn detection, returning voice-profile signals for emotion, vocal style, accent, age and pitch alongside the transcript.
Find alternatives to Realtime STT
What it does
- Speech to text
Features 7
- Voice ProfileTranscripts can carry the speaker's emotion, style, age and accent.
- Turn-takingSemantic and acoustic voice activity detection decides when the speaker has finished.
- Custom vocabularyLists up to 100 names and domain terms to bias recognition toward them.
- Speaker diarizationLabels every word with who said it and when, live over WebSocket or async for recordings.
- Recordings and videoAsync jobs take files up to 512 MB by URL or upload, including video files.
- Language hintsBiases recognition toward a language the user is already known to speak.
- Zero Data RetentionAudio and transcripts are processed in real time and never stored.
Sources
- Pricing
-
"STT 1 $0.15/hr" on On-Demand and $0.10/hr on Creator through Growth; "Inworld STT-1 is $0.10 per hour on paid plans, from $0.15 on-demand" (product page). Pricing page plan cards: On-Demand ("Start free", pay as you go), Creator $25/mo, Builder $100/mo, Developer $300/mo, Growth $1,500/mo, each granting equal monthly credits, and Enterprise "Custom pricing, limits & terms" with "contact sales". The only free allowance on the cards is "Up to 70 min TTS included", which names TTS, so no free model is recorded for STT.
- Description
-
Official documentation · 11 Oct 2026
"Voice profiling extracts emotion, vocal style, accent, age, and pitch from raw audio"; "Stream audio in real time, transcribe complete files, or extract voice profile signals — all through one unified API"; "30+ Languages". Docs list Turn Detection (https://docs.inworld.ai/llms.txt).
- What it does
-
Official documentation · 11 Oct 2026
"Realtime streaming recognition down to $0.10 per hour."
- Sold within
-
Self-serve plans with credit-card payment; credits "pay for usage across all Inworld products", no parent offering.
- Name
-
Official documentation · 11 Oct 2026
Page heading "Realtime STT"; model "Inworld STT-1".
- URL
-
Official documentation · 11 Oct 2026
Product page "Speech-to-Text: Realtime Streaming STT API", listed as "Realtime STT" in the site's product links.
- Deployment
-
Official documentation · 11 Oct 2026
Hosted WebSocket and synchronous endpoints.
- Interfaces
-
Official documentation · 11 Oct 2026
STT sync and WebSocket endpoints at api.inworld.ai; "inworld stt transcribe" in the Inworld CLI.
- Modalities
-
Official documentation · 11 Oct 2026
Audio in; transcript and voice-profile signals out.
- Intended for
-
Official documentation · 11 Oct 2026
Developers of consumer voice applications; enterprise tier on the pricing page.
Also from Inworld AI
-
Realtime TTS API service
Text-to-speech API (Realtime TTS-2 and TTS-2 Flash) with voice cloning and voice design, billed per million characters.
-
Realtime API API service
Speech-to-speech voice-agent API in which one WebSocket session runs Inworld speech recognition with voice profiling, a chosen LLM from 100+ with tool calling and turn detection, and Realtime TTS-2 voice output.
-
Realtime Router Platform
OpenAI-compatible LLM gateway that sends each request to one of 100+ models from OpenAI, Anthropic, Google and others by rules on user attributes, context, A/B splits or cost, with failover and provider rates passed through at zero markup.
-
Inworld Compute Infrastructure service
Dedicated NVIDIA B200 GPUs for high-volume realtime workloads such as LLM inference, dedicated TTS serving and custom model hosting, with Kubernetes access or Inworld-managed deployment, and deployed models routable through Inworld Router.
-
Inworld Inference Model API
Inworld Inference provides API access to text, image, video and decision models.
Open Inworld AI in the directory
Something wrong here? Send a correction — quote this product id: inworld-realtime-stt.