API Guides & TutorialsText to Speech

Text-to-Speech Rest API

Synchronous Processing

Convert text to speech with immediate response. Best for quick conversions and testing. Features include:

  • Instant audio generation
  • Multiple voice options
  • Customizable speech parameters
  • Various audio formats

API Features

Key Features
  • Multiple speaker voices
  • Adjustable speech parameters
  • High-quality audio output
  • Natural prosody and intonation
Output Format
  • Multiple audio file formats
  • Base64 encoded string
  • Configurable sample rates
Speech Parameters
  • Pitch control
  • Speech rate adjustment
  • Language selection

Model Information

Bulbul v2

Our flagship text-to-speech model designed for Indian languages and accents.

Key Features:

  • Natural-sounding speech with human-like prosody
  • Multiple voice personalities
  • Multi-language support
  • Real-time synthesis capabilities
  • Fine-grained control over pitch, pace, and loudness
Language Support

Supports 11 Indian languages with BCP-47 codes:

Supported Languages:

  • English (en-IN)
  • Hindi (hi-IN)
  • Bengali (bn-IN)
  • Tamil (ta-IN)
  • Telugu (te-IN)
  • Kannada (kn-IN)
  • Malayalam (ml-IN)
  • Marathi (mr-IN)
  • Gujarati (gu-IN)
  • Punjabi (pa-IN)
  • Odia (od-IN)

Bulbul: Our Text to Speech Model

Bulbul is our state-of-the-art text-to-speech model that excels in generating natural-sounding speech with support for multiple Indian languages and various voice options.

Text to Speech Features

Basic Text to Speech Synthesis

Convert text to natural-sounding speech with high quality. Features include:

  • Multiple voice options
  • Support for Indian languages
  • Natural prosody and intonation
  • High-quality audio output
1from sarvamai import SarvamAI
2from sarvamai.play import save
3
4client = SarvamAI(api_subscription_key="YOUR_API_SUBSCRIPTION_KEY")
5# Convert text to speech
6audio = client.text_to_speech.convert(
7  target_language_code="en-IN",
8  text="Welcome to Sarvam AI!",
9  model="bulbul:v2",
10  speaker="anushka"
11)
12save(audio, "output1.wav")
Key Considerations
  • For numbers > 4 digits, use commas (e.g., ‘10,000’)
  • Enable preprocessing for better numbers, dates handling

API Response Format

request_id
string

Unique identifier for the request

audios
arrayRequired

Array of base64-encoded audio files in the specified format (default: WAV). Each string corresponds to one of the input texts.

Audio Formats Supported:

  • WAV (default)
  • MP3
  • Linear16
  • Mulaw
  • Alaw
  • Opus
  • FLAC
  • AAC

Note: The audio is encoded as a base64 string. Decode it to save as an audio file.