Text to Speech

Generate Speech (Text-to-Speech)

post

Generates audio from input text using text-to-speech (TTS) models. The response is a JSON object containing base64-encoded audio in the audios array (not a raw binary stream).

Only model and input are required. All other parameters are model-specific — for example sarvam/bulbul:v2 supports target_language_code, speaker, pitch, pace, loudness, speech_sample_rate, enable_preprocessing, output_audio_codec, temperature, and enable_cached_responses.

Tip: Supported parameters and their accepted values differ from one model to another. Call GET /api/v1/models and inspect each model's supported_parameters and supported_params_details to see exactly which fields it accepts and the allowed values, ranges, or enums.

Authorizations

AuthorizationstringRequired

FastRouter API Key. Get yours at https://fastrouter.ai

Format: Authorization: Bearer YOUR_API_KEY

Body

modelstringRequired

TTS model in provider/model format.

Example: sarvam/bulbul:v2

inputstringRequired

The text to convert to speech.

Example: The quick brown fox.

target_language_codestringOptional

Model-specific (e.g. Sarvam). BCP-47 language code of the output speech (e.g. en-IN, hi-IN).

Example: en-IN

speakerstringOptional

Model-specific (e.g. Sarvam). The speaker voice to use.

Example: anushka

pitchnumberOptional

Model-specific (e.g. Sarvam). Adjusts the pitch of the generated speech.

pacenumberOptional

Model-specific (e.g. Sarvam). Adjusts the speed of the speech (e.g. 0.5x to 2.0x).

Example: 1

loudnessnumberOptional

Model-specific (e.g. Sarvam). Adjusts the loudness of the generated speech.

speech_sample_rateintegerOptional

Model-specific (e.g. Sarvam). Output audio sample rate in Hz.

Example: 22050

enable_preprocessingbooleanOptional

Model-specific (e.g. Sarvam). Enables text normalization / preprocessing before synthesis.

output_audio_codecstringOptional

Model-specific (e.g. Sarvam). The audio codec/format of the response.

temperaturenumberOptional

Model-specific. Sampling temperature for generation.

enable_cached_responsesbooleanOptional

Model-specific (e.g. Sarvam). Allows returning a cached response for identical requests.

Responses

200

The generated speech. Returns a JSON object containing the base64-encoded audio (not a raw binary stream).

application/json

audiosstring[]Optional

Array of base64-encoded audio clips (WAV). Usually one entry.

modelstringOptional

The model used to generate the audio.

Example: sarvam/bulbul:v2

providerstringOptional

The upstream provider that served the request.

Example: sarvam

400

Bad Request - The request is malformed. This could be due to missing parameters, invalid formats, or routing errors.

Note: the 400 body shape is not uniform. Validation errors return the structured object below, but routing/model errors may instead return a plain string: { "error": "<message>" }. A few endpoints (e.g. some file operations) may return a plain-text body rather than JSON.

application/json

401

Invalid Credentials - Your API key is invalid, missing, or disabled. Check your credentials.

Note: the 401 error body uses code, message, param, and type (there is no status field), and type is invalid_request_error.

application/json

402

Insufficient Credits - Your account or API key has run out of credits. Add more credits and retry the request.

application/json

429

Rate Limited - You have exceeded your request limits (TPM/RPM). Slow down or increase your limits.

application/json

500

Internal Server Error

post/api/v1/audio/speech

POST /api/v1/audio/speech HTTP/1.1
Host: api.fastrouter.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 59

{
  "model": "sarvam/bulbul:v2",
  "input": "The quick brown fox."
}

{
  "audios": [
    "UklGRs..."
  ],
  "model": "sarvam/bulbul:v2",
  "provider": "sarvam",
  "usage": {
    "prompt_tokens": 5,
    "total_tokens": 5,
    "cost": 0.000075,
    "chat_id": "fr_29a0c9b3-f31f-4282-8078-58482380c7a5"
  }
}