Speech To Text Tools

GlobalStreaming

Test Together AI NVIDIA Parakeet TDT 0.6B v3 (global) on your own audio

Drop one real file in below and see what comes back — no account needed to watch it land. Everything this deployment accepts, and what Together AI publishes about it, is under the console.

Input Source

Need the words as you speak, not after the file? Compare the providers live — same models, streaming, billed by the second.

Click or drag audio file here

Supports MP3, M4A, WAV, OGG

Up to 30 minutes of audio; longer recordings accepted up to 4 hours.

Configuration

Advanced Options
Not supported by all selected
Not supported by all selected

Provides a hint for the minimum and maximum number of expected speakers to improve diarization accuracy.

Not supported by all selected

Boosts the recognition probability of specific words or phrases, such as proper nouns or domain-specific terms. Provide one phrase per line.

Not supported by all selected
Not supported by all selected
Not supported by all selected
Vendor
Together AI
Model
nvidia/parakeet-tdt-0.6b-v3
Region
global
Global
Interface
Streaming
Billed by the second
OptionOn this deployment
Speaker diarizationLabels who spoke when, so a two-person recording comes back as a conversation.No
Speaker count hintTakes a minimum and maximum number of speakers to steer the labelling.No
Custom vocabularyTakes a list of terms — product names, jargon — to bias recognition toward.No
Automatic punctuationReturns punctuated, cased text rather than an unbroken lexical stream.No
Smart formattingWrites numbers, dates and currency as a reader expects them: twenty dollars as $20.No
Profanity filterMasks profane words in the returned transcript.No

What this deployment accepts through our API. A no means the option is not offered on this model here — not that the vendor has never shipped it.

It will also identify the language itself when you do not name one.

Live transcription is metered separately from whole files at every vendor here, and we have not published that sheet yet — so there is no honest figure to put on this page. The live comparison quotes a budget in seconds before it opens a session, and counts it down while it runs. What we charge is on our pricing page.

High-throughput multilingual NVIDIA Parakeet transcription hosted by Together AI

  • sync
  • file
  • multilingual
  • auto-language
  • timestamps
  • nvidia
  • parakeet
  • high-throughput

Together AI NVIDIA Parakeet TDT 0.6B v3 (global) documentation · Every model and region we test · Compare all 11 on one file