Migrating Text-to-Speech from Cartesia to Sarvam

This guide covers migrating Cartesia text-to-speech API calls to Sarvam. If you’re building a full voice agent rather than replacing individual TTS calls, start from the LiveKit or Pipecat voice agent build guides instead: they aren’t a 1:1 API swap and aren’t covered here.

Quick start

Base URL and auth header change the same way for every Cartesia migration, so they’re folded in here rather than in a separate page:

With that, replace the synthesis call and add the required language code:

1
from cartesia import Cartesia
2
3
client = Cartesia(api_key="YOUR_CARTESIA_API_KEY")
4
5
response = client.tts.generate(
6
    model_id="sonic-3.5",
7
    transcript="Welcome to our platform!",
8
    voice={
9
        "mode": "id",
10
        "id": "e07c00bc-4134-4eae-9ea4-1a55fb45746b",
11
    },
12
    output_format={
13
        "container": "wav",
14
        "encoding": "pcm_f32le",
15
        "sample_rate": 44100,
16
    },
17
)
18
19
response.write_to_file("output.wav")

The REST response is JSON with a base64 audios array, not a file. Decode .audios[0] before writing it out; see the REST API guide for the full decode snippet.

The rest of this page covers the full endpoint and parameter mapping, streaming, pronunciation dictionaries, and common mistakes.

Endpoint map

Parameter concept map

Streaming

Pronunciation dictionary

Both platforms use plain text-to-alias substitution rather than phonetic transcription, so the underlying concept carries over directly:

Since both dictionaries are simple text replacements, porting entries over is mostly a data migration, not a rewrite: copy each text/alias pair into Sarvam’s format and nest it under the right target_language_code. See the Pronunciation Dictionary guide for the full format and upload flow.

What’s different by design

• Ready-to-use voices, no cloning step. Sarvam ships a curated, named set of 30+ Bulbul v3 voices, professionally tuned and ready to call immediately, with no per-request cloning or training step to manage.
• Plain speaker names, no voice object. Sarvam’s speaker is a lowercase name you pick straight from the Voices page, rather than a {"mode": "id", "id": "<uuid>"} object you construct or fetch from /voices first.
• Flat output settings. speech_sample_rate and output_audio_codec are top-level params rather than a nested output_format object, so there’s less request-building code either way.
• One continuous pace control. pace works the same way across bulbul:v2 and bulbul:v3, rather than switching between a slow/normal/fast enum on older models and a continuous 0.6-1.5 float on newer ones.
• Explicit language targeting. Every Sarvam request carries target_language_code, so pronunciation and prosody are correct by design on every call, especially valuable for Hindi, Hinglish, and other code-mixed Indian-language text.
• Indian language depth is Sarvam’s specific strength. Sarvam covers Hindi plus 9 other Indian languages (Bengali, Tamil, Telugu, Kannada, Malayalam, Marathi, Gujarati, Punjabi, Odia), natively tuned for code-mixed input like Hinglish, alongside dedicated verbatim, translit, and codemix modes on the speech-to-text side.

Full example

A small wrapper function, before and after, showing the complete set of changes together:

1
from cartesia import Cartesia
2
3
client = Cartesia(api_key="YOUR_CARTESIA_API_KEY")
4
5
def synthesize(text: str, out_path: str) -> None:
6
    response = client.tts.generate(
7
        model_id="sonic-3.5",
8
        transcript=text,
9
        voice={"mode": "id", "id": "e07c00bc-4134-4eae-9ea4-1a55fb45746b"},
10
        output_format={"container": "wav", "encoding": "pcm_f32le", "sample_rate": 44100},
11
    )
12
    response.write_to_file(out_path)

Common mistakes

See also

• Migration overview: base URL, auth, and SDK client changes
• Migrating Speech-to-Text
• Which Text-to-Speech API to Use
• TTS Best Practices
• Voices
• Pronunciation Dictionary
• Errors & Troubleshooting