Introducing Parrot: Ringg’s speech-to-text model for production-grade voice agents. Capture Hindi-heavy and noisy real-world conversations with low-latency inference, stronger transcript quality, and Hindi validation built for downstream workflows.
No reviews yetBe the first to leave a review for Parrot Speech-to-text API
FramerLaunch websites with enterprise needs at startup speeds.
Promoted
Congratulation on the launch! Btw, when I mix English with Hindi, I observed its little biased towards transcribing English in Hindi (using Devnagri glyph). Latency is impressive
For code-mixed conversations where the dominant language is Hindi, this can happen but when English is the dominant language, it should work as expected.
Haha, how can something be this useful and this scary simultaneously!? As someone with a name most humans can't spell right, I look forward to the day when this is no longer an issue.
Report
Hunter
Exactly! Names are where STT gets very real very fast.
A big part of Parrot’s focus is making these real-world details more reliable, especially in Indian conversations.
Does it handle multiple speakers and diarization, or is it single channel transcripts only for now?
Report
Hunter
Hi @karimbenkeroum It is single channel transcripts only for now, however multiple speakers and diarization are a part of the roadmap and will be released with v2.
Report
Just tried this out, amazing speed and accuracy. Great work!
Report
Hunter
Thanks Vedant, really appreciate you trying it out!
Speed + accuracy was the core goal for us because voice agents need both. A transcript has to be right, but it also has to arrive fast enough to keep the conversation natural.
Congratulation on the launch! Btw, when I mix English with Hindi, I observed its little biased towards transcribing English in Hindi (using Devnagri glyph). Latency is impressive
Thanks @ashishkingdom ! That’s a fair observation.
For code-mixed conversations where the dominant language is Hindi, this can happen but when English is the dominant language, it should work as expected.
This is one of the expected behaviours.
Private Resume Builder
Haha, how can something be this useful and this scary simultaneously!? As someone with a name most humans can't spell right, I look forward to the day when this is no longer an issue.
Exactly! Names are where STT gets very real very fast.
A big part of Parrot’s focus is making these real-world details more reliable, especially in Indian conversations.
mailX by mailwarm
Does it handle multiple speakers and diarization, or is it single channel transcripts only for now?
Hi @karimbenkeroum
It is single channel transcripts only for now, however multiple speakers and diarization are a part of the roadmap and will be released with v2.
Just tried this out, amazing speed and accuracy. Great work!
Thanks Vedant, really appreciate you trying it out!
Speed + accuracy was the core goal for us because voice agents need both. A transcript has to be right, but it also has to arrive fast enough to keep the conversation natural.
Riff
Best for voice AI use case!!
Try this out with easy to integrate package https://www.ringg.ai/dashboard/stt