$0.003per minute
3.9AA Speech to text
—released
en, es, fr +27Languages
YesSpeaker diarization
$0.003 / minPer audio minute
Exact native tariff; see source for billing scope.Price covers
Ranking?
Full ranking →···
24Universal, AssemblyAI3.826Inworld STT 13.927GPT-4o Transcribe4Strong at
Alternatives?
ModelScoreCostPriceWhat changes
CheaperMAI Transcribe 2+95%-33%$0.002
BetterFun Realtime ASR Preview×2.3——Languages: not verified+2
OpenWhisper Large v2same+140%$0.006Speaker diarization: not verified+1
CheaperGrok Voice Transcribe 2.0+70%-33%$0.002SCheaperSoniox v5 Asyncsame-34%$0.002ModelScoreCostPriceWhat changes
MAI Transcribe 2+95%-33%$0.002Grok Voice Transcribe 2.0+70%-33%$0.002SSoniox v5 Asyncsame-34%$0.002MModulate STT Batch English VFastsame-83%$0Languages: not verified+1
Canary Qwen 2.5B, NVIDIAOpensame-70%$0.001Languages: loses es, fr, de +26+1ModelScoreCostPriceWhat changes
Fun Realtime ASR Preview×2.3——Languages: not verified+2ModelScoreCostPriceWhat changes
Whisper Large v2Opensame+140%$0.006Speaker diarization: not verified+1Canary Qwen 2.5B, NVIDIAOpensame-70%$0.001Languages: loses es, fr, de +26+1Parakeet TDT 0.6B V3, TogetheraiOpensame-40%$0.002Languages: loses zh, ja, ko +12+1Whisper Large v3 TurboOpensame-73%$0.001Speaker diarization: not verifiedWizper Large v3Opensame-80%$0.001Speaker diarization: not verifiedBenchmarks
in Speech & VoiceFAQ
How much does Inworld STT 1 cost?›
$0.003 per minute.
Is Inworld STT 1 free to use?›
There is no free API; it costs $0.003 per minute.
How good is Inworld STT 1, and what is it best at?›
#24 of 51 in Speech to text.
Is Inworld STT 1 better than Universal, AssemblyAI?›
On AA Speech to text · Recorded audio word error rate, Inworld STT 1 scores 3.9 vs 3.8 — about the same. It is 0% more expensive.
Is Inworld STT 1 open source?›
No, Inworld STT 1 is a closed model available through an API. The closest open-weights option here is Whisper Large v2.
What is Inworld STT 1?›
Inworld STT 1 is a closed speech & voice model from Inworld.
What are the best alternatives to Inworld STT 1?›
MAI Transcribe 2 (cheaper), Fun Realtime ASR Preview (better), Whisper Large v2 (open weights).