Skip to contentLaunchAlania-1 and Duyu are free for one month.See the offer

Turkish speech.Live transcripts.One API.

Duyu turns Turkish speech into text. Alania turns text into speech. Give your application a voice.

ALANIADUYU
Start freeRead the docs
DUYU · Speech to text

A word for every voice.
Speak for yourself.

Appointments, addresses, a name spelled out loud. Try the Turkish your callers actually speak.

A little inspiration.

“Yarın saat 14:30'daki diş randevumu 16:00'ya alabilir miyiz?”

Your microphone.

Ready to listen

In your words.

Explore Duyu
Alania · Text to speech

A voice for every word.
Hear it for yourself.

Dates, questions, a little reassurance. Try the Turkish your application actually uses.

Your words60/280
Make it sound like your application.
Alania’s voiceAlania · Türkçe

“Randevunuz 29.10.2026 tarihinde saat 14:05 için oluşturuldu.”

Ready when you are24 kHz · WAV

AI-generated audio. Prerecorded samples are labeled during playback.

Alania
For developers

Two models.
One way to build.

One API key. Text in, speech out. Audio in, text out.

curl https://voice.patientdesk.ai/v1/audio/speech \
  -H "Authorization: Bearer pd_live_..." \
  -H "Content-Type: application/json" \
  -d '{ "model": "alania-v1",
        "input": "Randevunuz yarın saat 14:05 için oluşturuldu.",
        "voice": "alania", "response_format": "wav" }' \
  --output randevu.wav
POST /v1/audio/speech
Alania · Text to speech

Generate Turkish speech

Explore the API
curl https://voice.patientdesk.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer pd_live_..." \
  -F file=@kayit.m4a \
  -F response_format=json
POST /v1/audio/transcriptions
Duyu · Speech to text

Transcribe Turkish audio

Explore the API
The details matter

Clear comparisons.
A closer look at performance.

Explore Turkish transcription across three datasets, then see what each timing measure means.

voicedata-TR

235 multi-speaker Turkish clips

  • PatientDesk STT8.54%
  • whisper-large-v310.97%
  • whisper-large-v3-turbo11.19%
  • Qwen3-ASR-1.7B13.65%
  • mihuai/turkish-stt19.89%
  • Qwen3-ASR-0.6B22.30%

Word error rate · Turkish-normalized · Lower is better

Every moment, explained.

Time to first audio310ms

TTS request to first audio chunk · p50

Final transcript latency120ms

End of speech segment to final transcript · p50

File transcription speedup to50×

Faster than real time · audio duration ÷ processing time

Different measures for different parts of the workflow.

Launch offer

One month free.
Both models.

To mark the launch, Alania-1 and Duyu are free for one month. Usage pricing starts after that.

Launch campaign · 1 month

Launch offer

Both models, free for one month.

Duyu$0.04/minute$0
Alania$0.06/1,000 characters$0

For the first month, both models.

  • Alania-1 and Duyu, free for one month
  • REST and live streaming
  • One API key for both models
  • No card required
Start free

Usage-based

After the first month, keep building at usage prices.

Duyu$0.04/minute
Alania$0.06/1,000 characters
  • Starts after the free month
  • Pay only for additional usage
  • Same API, more capacity
  • Billed monthly
Start free

Enterprise

For your infrastructure and your team.

Let’s talk
  • Custom quotas and concurrency
  • Deployment on your infrastructure
  • Data-processing terms
  • Priority support
Contact sales

Additional usage is billed monthly. Prices exclude VAT.

Get started

Create your key.
Send a request.

Start free
Read the docsContact sales