POST /v1/audio/speech
Convert a text string into spoken audio. The response is a binary audio file in the format specified by response_format. You can stream the audio by reading the response body incrementally.Request parameters
The text-to-speech model to use. Use the list models endpoint for available TTS model IDs. The text to synthesize into speech. Maximum length depends on the model.
The voice to use for synthesis. Available voices depend on the model. Common options include "alloy", "echo", "fable", "onyx", "nova", and "shimmer".
The audio format for the output. Supported values: "mp3", "opus", "aac", "flac", "wav", and "pcm".
Playback speed of the generated audio, between 0.25 and 4.0. Values above 1.0 speed up speech; values below 1.0 slow it down.
Example
The response body is the raw audio binary. Pipe it directly to a file:curl https://tokmodel.com/v1/audio/speech \
--request POST \
--header "Authorization: Bearer YOUR_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "openai/tts-1",
"input": "Welcome to TokModel, your unified LLM API gateway.",
"voice": "nova",
"response_format": "mp3",
"speed": 1.0
}' \
--output speech.mp3
POST /v1/audio/transcriptions
Transcribe an audio file into text. The audio file is uploaded as a multipart form field. The returned text is in the language spoken in the audio file unless you override it with the language parameter.Request parameters
The audio file to transcribe, uploaded via multipart/form-data. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.
The transcription model to use. Use the list models endpoint for available options (for example, openai/whisper-1). The language of the audio in ISO-639-1 format (for example, "en", "fr", "de"). Providing this improves accuracy and speed.
The format of the transcription output. One of "json", "text", "srt", "verbose_json", or "vtt".
Sampling temperature between 0 and 1. Lower values produce more accurate, deterministic transcriptions.
Example
curl https://tokmodel.com/v1/audio/transcriptions \
--request POST \
--header "Authorization: Bearer YOUR_API_KEY" \
--form "file=@/path/to/recording.mp3" \
--form "model=openai/whisper-1" \
--form "language=en" \
--form "response_format=json"
Response
{
"text": "The quick brown fox jumps over the lazy dog."
}
POST /v1/audio/translations
Transcribe an audio file and translate the content into English in a single step. This endpoint always returns English text, regardless of the language spoken in the audio file.Request parameters
The audio file to translate, uploaded via multipart/form-data. Supported formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm.
The translation model to use.
The format of the translation output. One of "json", "text", "srt", "verbose_json", or "vtt".
Sampling temperature between 0 and 1.
Example
curl https://tokmodel.com/v1/audio/translations \
--request POST \
--header "Authorization: Bearer YOUR_API_KEY" \
--form "file=@/path/to/french-audio.mp3" \
--form "model=openai/whisper-1" \
--form "response_format=json"
Response
{
"text": "Hello, my name is Marie and I live in Paris."
}
