# Inworld STT (slim)

> Inworld's speech-to-text API runs its inworld/inworld-stt-1 model in 30 languages over synchronous HTTP, bidirectional WebSocket streaming and asynchronous jobs, returning Voice Profile signals (age, emotion, pitch, accent) and turn detection alongside the transcript.

- Full: https://www.anchorterminal.com/tools/inworld-stt.md (~7,250 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/inworld-stt.json · canonical https://www.anchorterminal.com/tools/inworld-stt
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/inworld-stt#pricing · reviews https://www.anchorterminal.com/tools/inworld-stt#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**C · 54.7/100 · rank #895 of 1486 · #16 in Speech-to-text · not agent-ready · confidence medium**


Assessment: Inworld STT costs $0.10 to $0.15 an hour with 400 free minutes, and covers files, live streams and async jobs in 30 languages with Voice Profile signals. There is no machine-readable spec, no public STT changelog and no readable status history, and diarisation is still experimental.

## Facts

- Kind: Model API · vendor: Inworld AI · category: Speech-to-text · legal entity: Theai, Inc. dba Inworld AI · provenance 75/100
- Local only (HTTP, websocket): npm `@inworld/cli`
- Auth: API key · pricing: Pay per use · x402: no · licence: unknown
- Benchmark probes: not run yet, so Performance is pending
- Surface listed: The STT API at api.inworld.ai/stt/v1, read from docs.inworld.ai (llms.txt, Markdown pages, API reference), inworld.ai/pricing and inworld.ai/speech-to-text on 6 November 2026, with terms, privacy, security and status as read for inworld-tts on 4 November. No account was made and no request was sent
- Model: `inworld/inworld-stt-1`. The billing page also bills third-party STT models through the same API by the duration the provider reports, such as `groq/whisper-large-v3` with a ten-second minimum
- Languages: 30, with `language` as a hint the model may not follow; BCP-47 codes are reduced to the base code
- Audio: LINEAR16, MP3, OGG_OPUS, FLAC or AUTO_DETECT, inline Base64 or multipart upload on the sync route
- Signals: Voice Profile (age, emotion, pitch, vocal style, accent), turn detection automatic or manual, word timestamps and experimental diarisation
- Same company: Inworld TTS is listed as inworld-tts. The Realtime API, listed as inworld-realtime, bills its speech recognition as STT on this model
- MCP server: Ships inside `@inworld/cli` (1.5.0, 29 October 2026, MIT) as `inworld mcp`, with an STT transcription tool among TTS, voice and LLM tools
- Prices: STT-1, On-Demand $0.0025 per minute of audio; STT-1, paid plans $0.0017 per minute of audio

- Scores: Reliability 60, Performance pending, Schema & documentation 54, Agent ergonomics 56, Security & auth 63, Payments & pricing 40, Task success pending, Maintenance & community 41, Transparency & trust 60 · total over the 7 assessed categories
- Why: Reliability, Hosted reading of the checklist. · Schema & documentation, No OpenAPI or other machine-readable file. · Agent ergonomics, API reading of the checklist. · Security & auth, Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Read as a model. · Transparency & trust, Closed service with clear terms naming Theai, Inc.
- Sources: 13, open questions: 4, both in the full twin
- Capabilities: speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages
- JSON: https://www.anchorterminal.com/api/v1/tools/inworld-stt.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/inworld-stt.svg` or a link to https://www.anchorterminal.com/tools/inworld-stt from a page on inworld.ai or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: Discord https://discord.gg/inworld; support@inworld.ai; https://docs.inworld.ai/portal/support; https://docs.inworld.ai/; more in the full twin

## Before you call it

1. Send the Base64 credential as-is in `Authorization: Basic`; don't encode it again
2. Wrap the first WebSocket message in `transcribeConfig`, because a malformed first frame closes the socket with 1005 and no error
3. Use `POST /stt/v1/transcribe:async` for files over about 16 MB and collect the transcript within 7 days
4. Retry 429 or gRPC code 8 with exponential backoff and jitter, and stay within the plan's streaming concurrency
5. Stop sending audio when nobody speaks, since streams are billed for every second sent

## Connect

```bash
npm install -g @inworld/cli
```

```bash
claude mcp add inworld -- inworld mcp
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Azure AI Speech speech-to-text | BB | 75.1 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/azure-speech-to-text.min.md |
| OpenAI Speech to Text | BB | 75 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/openai-speech-to-text.min.md |
| Deepgram Speech-to-Text (Nova-3, Flux) | BB | 74.4 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/deepgram-stt.min.md |
| Amazon Transcribe | BB | 73.6 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/amazon-transcribe.min.md |
| ElevenLabs Scribe Speech to Text API | BB | 73 | speech.stt, speech.streaming, speech.batch, speech.diarisation, speech.languages | https://www.anchorterminal.com/tools/elevenlabs-scribe.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)