Skip to contentLaunchAlania-1 and Yanki are free for three months.See the offer
AlaniaText to speech

Give your words
a Turkish voice.

Turn text into spoken Turkish with Alania. Natural phrasing, clear numbers, and streaming audio for your next voice experience.

Try AlaniaAPI reference
TurkishStreaming audioWAV & Opus
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.

Capabilities

Made for the details
that make a conversation.

Alania
Sample recording

Endişenizi anlıyorum; birlikte sakin sakin bir çözüm bulacağız.

length
6.1 s

It talks, it doesn't read.

In practice
A patient should feel they are talking to a person, not a phone menu. If stress, pauses and pace are off, even correct information sounds artificial.
Alania's approach
Alania is trained on Turkish conversational speech; it infers sentence stress and breath points from the text. No SSML tags needed.
Performance

First audio.
Then the rest.

Start playing the response while Alania generates the remaining audio. Stream it to a caller, an assistant, or your application.

API reference
Time to first audio~310ms

Request start to first audio chunk · p50

Characters per API request5,000

One request. One consistent voice.

Different measures for different parts of the workflow.

API reference

Your text in.
Spoken Turkish out.

Send a text request, choose your quality and format, and consume the audio as it arrives.

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

Request parameters

Request parameters
ParameterRequirementDetails
inputrequiredUp to 5000 characters.
streamoptionaltrue sends the audio as it is generated.
response_formatoptionalwav (default), pcm, mp3, opus, flac, aac.
voiceoptionalalania; one locked voice.

Every response carries an x-disclosure: ai-generated header.

Launch offer

Three months free.
Both models.

To mark the launch, Alania-1 and Yanki are free for three months. Usage pricing starts after that.

Launch campaign · 3 months

Launch offer

Both models, free for three months.

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

For the first three months, both models.

  • Alania-1 and Yanki, free for three months
  • REST and live streaming
  • One API key for both models
  • No card required
Start free

Usage-based

After the three months, keep building at usage prices.

Yanki$0.04/minute
Alania$0.06/1,000 characters
  • Starts after the three free months
  • 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.

Better together

Let your application listen, too.

One account. Two sides of the conversation.

Explore Yanki
Get started

Create your key.
Send a request.

Start free
Read the docsContact sales