RuwanaRuwanaPlatform API
Ruwana API / Avatar API
AI Avatar API

Talking avatars with voice, emotion and performance direction.

Create avatar video from one image and either text-to-speech or uploaded audio. Ruwana measures the prepared audio server-side, then runs the selected 720p or 1080p production tier as a durable asynchronous request.

Full Avatar docsView pricing
TTS included12 voices7 emotionsSpeech rate 80–130%3–30 seconds

Choose generated speech or your own audio

Every request requires one avatar image and exactly one speech source. The client never supplies authoritative billing duration.

Text-to-speech

Send speech plus a public Ruwana voice name. TTS is included in the Avatar price.

  • Speech text up to 3000 characters
  • Voice and speech-rate controls
  • Prepared audio is measured server-side before Avatar submission
  • Emotion and performance direction remain visual-performance controls

Uploaded audio

Send audio instead of speech when the voice track is already prepared.

  • MP3, WAV, M4A/MP4 audio accepted by the public contract
  • Actual audio duration is measured server-side
  • 3–30 second Avatar production window
  • The same durable status and billing rules apply

Two native Avatar tiers

Standard and Pro are distinct public production tiers. TTS is included in both when speech text is used.

TierResolutionPriceBillingRetention
Standard720p$0.11/secPrepared audio duration7 days
Pro1080p$0.22/secPrepared audio duration7 days

Public voice and performance controls

The API exposes stable Ruwana names across the public production contract.

Voices

AxelMayaSiennaEthanMarcusEliasNovaCelesteTobyLilaKaiMimi

Use the voice field with speech text.

Emotion & delivery

NeutralConfidentHappyAngrySadPresenterLuxury
  • voice_speed: 80–130, default 100
  • emotion: one supported public value
  • prompt: free-form performance and visual direction

Example: speech-driven Avatar

The example uses public Ruwana controls only.

curl https://platform.ruwana.studio/v1/avatar/generate \
  -H "Authorization: Bearer $RUWANA_API_KEY" \
  -H "Idempotency-Key: avatar-001" \
  -F "avatar_image=@portrait.jpg" \
  -F "speech=Welcome to the new collection." \
  -F "resolution=720p" \
  -F "voice=Maya" \
  -F "voice_speed=100" \
  -F "emotion=Confident" \
  -F "prompt=Natural premium presenter delivery with restrained gestures."

Asynchronous from speech preparation to final video

Speech generation and Avatar rendering are tracked durably. Polling status never replays the production submit.

Create the request

POST /v1/avatar/generate validates the image, speech source and public controls.

Prepare and measure audio

Platform generates TTS when requested or measures uploaded audio, then establishes the server-authoritative billable duration.

Read the same request

Use GET /v1/requests/{request_id} through preparation, render and terminal state.

Archive the result

Successful MP4 delivery is retained for 7 days. Long-term copies belong in your own storage.

Talking Avatar capability

Understand speech vs uploaded audio, public controls, duration and production tiers.

Explore Talking Avatar →

Build Avatar generation without managing separate voice infrastructure.

Use Ruwana speech, voice and performance controls through the same organization API key and wallet as Image and Motion.

Open QuickstartOpen Platform