Synthesize speech

POST https://api.vakyam.ai/v1/tts/generate

Synthesizes the full input text and returns base64-encoded audio in a JSON envelope. The entire audio is generated before the response is returned. For lower latency, see HTTP streaming or the WebSocket endpoint.

voice_name is deprecated and will be removed after a migration window. Use the new voice parameter instead — it accepts a preset voice name (e.g. Archana) or a custom voice ID beginning with vc_. voice_name remains temporarily accepted for preset voices only and cannot be combined with voice.

Ask AI about this page

Authorization

header Authorizationstringrequired

Bearer token: Bearer vak_live_<key>.

Body

Request body

123456789{
  "text": "வணக்கம், நான் வாக்யம் AI பேசுகிறேன்.",
  "model_id": "raaga-v1",
  "voice": "Archana",
  "language": "ta-IN",
  "output_format": "mp3",
  "sample_rate": 24000,
  "speed": 1.0
}

body textstringrequired

Text to synthesize. Maximum 3000 Unicode characters.

body model_idstringrequired

Model identifier. Must be raaga-v1.

body voicestringrequired

Voice selector. A preset voice name (e.g. Archana) or a custom voice ID beginning with vc_. A preset voice must form a valid pair with language — see Voices. Send either voice or the deprecated voice_name, not both.

body voice_namestringdeprecated

Deprecated — use voice instead. Temporarily accepted for preset voices only (it cannot select vc_ custom voices) and will be removed after the migration window.

body languagestringrequired

BCP 47 language code: en-IN, hi-IN, ta-IN, te-IN, kn-IN, mr-IN, gu-IN, or bn-IN.

body output_formatstringdefault: mp3

Audio format: mp3, wav, pcm, or mulaw.

body sample_rateintegerdefault: 24000

Output sample rate in Hz. One of 8000, 16000, 24000, or 48000.

body speednumberdefault: 1.0

Playback speed multiplier, 0.5–2.0.

Response

123456{
  "audio": "SUQzBAAAAAAA...",
  "format": "mp3",
  "duration_seconds": 2.4,
  "characters_used": 36
}

audiostring

Base64-encoded audio data. Decode it to get the raw audio bytes.

formatstring

Output format of the returned audio.

duration_secondsnumber

Duration of the synthesized audio in seconds.

characters_usedinteger

Unicode characters consumed from your credit balance.

Request example

12345678910curl https://api.vakyam.ai/v1/tts/generate \
  -H "Authorization: Bearer $VAKYAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "வணக்கம், நான் வாக்யம் AI பேசுகிறேன்.",
    "model_id": "raaga-v1",
    "voice": "Archana",
    "language": "ta-IN",
    "output_format": "mp3"
  }'

Response example

123456{
  "audio": "SUQzBAAAAAAA...",
  "format": "mp3",
  "duration_seconds": 2.4,
  "characters_used": 36
}