TTS Inference
Text-to-Speech
Text-to-Speech (REST)
Synchronous text-to-speech with full audio returned in one response.
POST
TTS Inference
Overview
Get the complete synthesized audio in one response. Best for downloads or batch processing. For streaming playback, see TTS Streaming or TTS Realtime.Passing numbers, IDs, dates, or currency as raw strings causes mispronunciations. See the Input Formatting Guide for correct formatting of phone numbers, account numbers, PINs, Aadhaar, vehicle registration numbers, GSTIN, currency, and more.
Models
Endpoint
Authentication
Request Parameters
string
required
The text to synthesize into speech. Pass numbers, dates, and currency as spoken words to avoid mispronunciations — see Input Formatting Guide.
string
required
Set to
timbre-v2.5.string
required
Voice name from the Timbre v2.5 catalog. See the Voice Catalog for preferred voices by language. Example:
Nalini, Kaveri, Deepak.string
required
Language of the input text. Controls text normalization and routing.
number | string
default:"1.0"
Playback speed multiplier. Numeric range:
0.85 (slowest) to 1.15 (fastest). String shortcuts: "slow" = 0.85, "medium" = 1.0, "fast" = 1.15.object
Controls the format of the returned audio.
Audio Format Reference
Encoding aliases — produce identical output to the
container rows above:
bitrate only applies when container=mp3. container=mulaw/alaw override sample_rate to 8000 Hz.
Response
A successful request returns200 OK with raw binary audio in the format specified by audio_config.container.
Code Example
Available Voices
42 voices across 10 Indian languages, English, and Hinglish. See the full Voice Catalog for preferred voices by language, gender, persona, and description. Popular examples:Nalini (Hindi), Kaveri (English), Deepak (Hindi), Poorvi (Hinglish).
Python SDK
The official Python SDK handles authentication headers and binary audio responses automatically.Installation
Authentication
Synthesize Speech
Custom Audio Config
Authorizations
Headers
Body
application/json
Request body for TTS inference.
TTS model. Use timbre-v2.5. Timbre v2.0 is deprecated and will be removed soon.
Available options:
timbre-v2.5 Audio output configuration.
Voice name from the Timbre catalog.
Language code. Use auto, hi-IN, en-IN, hi-en, ta-IN, te-IN, kn-IN, ml-IN, mr-IN, pa-IN, bn-IN, or gu-IN.
Playback speed multiplier. Range: 0.85–1.15.
Response
Successful audio synthesis
The response is of type file.