Audio - Mesh API

Text to speech

audio.synthesize returns raw audio bytes.

Python
Node.js
Go

from meshapi import MeshAPI, SpeechParams

client = MeshAPI(base_url="https://api.meshapi.ai", token="rsk_...")

audio_bytes = client.audio.synthesize(
    SpeechParams(
        input="Hello from MeshAPI audio test.",
        model="sarvam/bulbul:v2",
    )
)

# audio_bytes is a bytes object
with open("output.wav", "wb") as f:
    f.write(audio_bytes)

const audio = await client.audio.synthesize({
  input: "Hello from MeshAPI audio test.",
  model: "sarvam/bulbul:v2",
});

// audio is a Uint8Array
import { writeFileSync } from "fs";
writeFileSync("output.wav", audio);

model := "sarvam/bulbul:v2"

audioBytes, err := client.Audio.Synthesize(ctx, meshapi.SpeechParams{
    Input: "Hello from MeshAPI audio test.",
    Model: &model,
})
if err != nil {
    log.Fatal(err)
}

os.WriteFile("output.wav", audioBytes, 0644)

Speech to text

audio.transcribe accepts raw audio bytes plus a filename hint for format detection.

Argument order differs by language:

Python: transcribe(bytes, TranscriptionParams, filename=)
Node.js: transcribe(audio, { model }, { filename })
Go: Transcribe(ctx, bytes, filename, TranscriptionParams)

Python
Node.js
Go

from meshapi import MeshAPI, SpeechParams, TranscriptionParams

# Generate audio first, then transcribe it
audio_bytes = client.audio.synthesize(
    SpeechParams(input="Hello from MeshAPI.", model="sarvam/bulbul:v2")
)

result = client.audio.transcribe(
    audio_bytes,
    TranscriptionParams(model="sarvam/saaras:v3"),
    filename="tts_output.wav",
)

print(result.text)

const audio = await client.audio.synthesize({
  input: "Hello from MeshAPI.",
  model: "sarvam/bulbul:v2",
});

const result = await client.audio.transcribe(
  audio,
  { model: "sarvam/saaras:v3" },
  { filename: "tts_output.wav" },
);

console.log(result.text);

model := "sarvam/bulbul:v2"
audioBytes, _ := client.Audio.Synthesize(ctx, meshapi.SpeechParams{
    Input: "Hello from MeshAPI.",
    Model: &model,
})

result, err := client.Audio.Transcribe(ctx, audioBytes, "tts_output.wav", meshapi.TranscriptionParams{
    Model: "sarvam/saaras:v3",
})
if err != nil {
    log.Fatal(err)
}
fmt.Println(result.Text)

Translate audio to English

POST /v1/audio/translations transcribes audio in any language and returns the text translated to English. It returns the same TranscriptionResponse (with a .text field) as transcription.

This is a distinct endpoint from the transcribe-and-translate helper (POST /v1/audio/transcriptions/translate). Use a speech model that supports translation — see the Models list. model is required.

Python
Node.js
Go

from meshapi import MeshAPI, AudioTranslationsParams

client = MeshAPI(base_url="https://api.meshapi.ai", token="rsk_...")

with open("french_audio.mp3", "rb") as f:
    audio_bytes = f.read()

result = client.audio.audio_translate(
    audio_bytes,
    AudioTranslationsParams(model="openai/whisper-large-v3"),
    filename="french_audio.mp3",
)

print(result.text)  # English translation

import { readFileSync } from "fs";

const audio = readFileSync("french_audio.mp3");

const result = await client.audio.translations(
  audio,
  { model: "openai/whisper-large-v3" },
  { filename: "french_audio.mp3" },
);

console.log(result.text); // English translation

audioBytes, _ := os.ReadFile("french_audio.mp3")

result, err := client.Audio.Translations(ctx, audioBytes, "french_audio.mp3", meshapi.AudioTranslationParams{
    Model: "openai/whisper-large-v3",
})
if err != nil {
    log.Fatal(err)
}
fmt.Println(result.Text) // English translation

Optional parameters: prompt (context hint), response_format (json, text, or verbose_json), and temperature (0–2).

List voices

Python
Node.js
Go

from meshapi import MeshAPI, ListVoicesParams

voices = client.audio.list_voices(ListVoicesParams(page_size=5))

const voices = await client.audio.listVoices({ page_size: 5 });

pageSize := 5
voices, err := client.Audio.ListVoices(ctx, &meshapi.ListVoicesParams{
    PageSize: &pageSize,
})

`ListVoicesParams` fields

Field	Type	Notes
`page_size`	integer	Results per page
`next_page_token`	string	Pagination cursor from the previous response
`search`	string	Filter by name
`voice_type`	string	`standard`, `cloned`, and so on
`category`	string	Voice category filter

Get a voice

Fetch a single voice by ID — GET /v1/audio/voices/{voice_id}.

Python
Node.js
Go

voice = client.audio.get_voice("voice-id")
print(voice)

const voice = await client.audio.getVoice("voice-id");
console.log(voice);

voice, err := client.Audio.GetVoice(ctx, "voice-id")
if err != nil {
    log.Fatal(err)
}
fmt.Println(voice)

Parameter reference

`SpeechParams` (text to speech)

Field	Type	Notes
`input`	string	Required. Text to synthesize.
`model`	string	Required. e.g. `sarvam/bulbul:v3`
`voice`	string	Voice ID or name
`response_format`	string	Audio format, e.g. `wav`, `mp3`, `pcm_24000`
`speed`	number	Playback speed multiplier

`AudioTranslationsParams` (translate to English)

Field	Type	Notes
`model`	string	Required. Translation-capable model
`prompt`	string	Context hint for the model
`response_format`	string	`json`, `text`, or `verbose_json`
`temperature`	number	0–2

​Text to speech

​Speech to text

​Translate audio to English

​List voices

​ListVoicesParams fields

​Get a voice

​Parameter reference

​SpeechParams (text to speech)

​AudioTranslationsParams (translate to English)

Text to speech

Speech to text

Translate audio to English

List voices

`ListVoicesParams` fields

Get a voice

Parameter reference

`SpeechParams` (text to speech)

`AudioTranslationsParams` (translate to English)