Audio
Convert text to natural-sounding speech with the audio endpoints
Audio
Generate natural-sounding speech from text. The audio API is OpenAI-compatible and returns audio bytes directly.
Text-to-Speech
Endpoint
POST https://api.assisters.dev/v1/audio/speechRequest Body
The TTS model to use. Example: assisters-tts-v1
The text to synthesize into speech. Maximum 4096 characters.
alloyThe voice to use. Options: alloy, echo, fable, onyx, nova, shimmer
mp3The output audio format. Options: mp3, opus, aac, flac, wav, pcm
1.0Playback speed multiplier. Range: 0.25 to 4.0.
Response
Returns raw audio bytes with Content-Type: audio/mpeg (or the format requested).
Example
curl https://api.assisters.dev/v1/audio/speech \
-H "Authorization: Bearer $ASSISTERS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "assisters-tts-v1",
"input": "Hello! Welcome to Assisters.",
"voice": "nova"
}' \
--output speech.mp3import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.assisters.dev/v1",
apiKey: process.env.ASSISTERS_API_KEY,
});
const response = await client.audio.speech.create({
model: "assisters-tts-v1",
input: "Hello! Welcome to Assisters.",
voice: "nova",
});
const buffer = Buffer.from(await response.arrayBuffer());
await fs.writeFile("speech.mp3", buffer);from openai import OpenAI
client = OpenAI(
base_url="https://api.assisters.dev/v1",
api_key=os.environ["ASSISTERS_API_KEY"],
)
response = client.audio.speech.create(
model="assisters-tts-v1",
input="Hello! Welcome to Assisters.",
voice="nova",
)
response.stream_to_file("speech.mp3")Audio Transcription
Endpoint
POST https://api.assisters.dev/v1/audio/transcriptionsRequest Body
The audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm
The transcription model. Example: assisters-stt-v1
ISO-639-1 language code (e.g. en, es, fr). Auto-detected if omitted.
jsonOutput format. Options: json, text, srt, vtt, verbose_json
Response
{
"text": "Hello, welcome to Assisters."
}Example
curl https://api.assisters.dev/v1/audio/transcriptions \
-H "Authorization: Bearer $ASSISTERS_API_KEY" \
-F "[email protected]" \
-F "model=assisters-stt-v1"