Audio (Speech & Transcription)

TIE provides OpenAI-compatible audio endpoints for speech-to-text (transcription) and text-to-speech (TTS). These are drop-in replacements for OpenAI's /v1/audio/transcriptions and /v1/audio/speech — any client that works with OpenAI's audio API works with TIE by changing the base URL.

All requests require a Bearer token from TIE Auth.

Speech-to-Text (Transcription)

Convert audio to text. TIE proxies to OpenAI Whisper and returns the transcript.

Endpoint

POST /v1/audio/transcriptions

Parameters

Send as multipart/form-data:

Parameter	Type	Default	Description
file	file	required	Audio file (mp3, mp4, mpeg, mpga, m4a, wav, webm)
model	string	whisper-1	Transcription model
language	string	null	ISO 639-1 language code (e.g. en). Improves accuracy if known.
prompt	string	null	Guide the model's style or continue a previous segment
response_format	string	json	Output format: json, text, srt, verbose_json, vtt
temperature	float	0.0	Sampling temperature (0–1). Lower is more deterministic.

Example

curl -X POST https://your-tie-host/v1/audio/transcriptions \
  -H "Authorization: Bearer $TOKEN" \
  -F file=@recording.webm \
  -F model=whisper-1

Response

Default (json format):

{
  "text": "Hello, I'd like to log my breakfast. I had oatmeal with blueberries."
}

With response_format=verbose_json, the response includes timestamps and segment-level detail.

AI SDK Integration

The Vercel AI SDK supports transcription via experimental_transcribe. Point the OpenAI provider at your TIE instance:

import { createOpenAI } from "@ai-sdk/openai";
import { experimental_transcribe as transcribe } from "ai";

const tie = createOpenAI({
  baseURL: "https://your-tie-host/v1",
  apiKey: "your-bearer-token",
});

const result = await transcribe({
  model: tie.transcription("whisper-1"),
  audio: audioBuffer, // Uint8Array, Buffer, base64 string, or URL
});

console.log(result.text);
// "Hello, I'd like to log my breakfast."

---

Text-to-Speech

Convert text to spoken audio. TIE proxies to OpenAI's TTS models and streams audio bytes back.

Endpoint

POST /v1/audio/speech

Parameters

Send as JSON:

Parameter	Type	Default	Description
model	string	gpt-4o-mini-tts	TTS model (gpt-4o-mini-tts, tts-1, tts-1-hd)
input	string	required	Text to convert to speech (max 4096 characters)
voice	string	alloy	Voice: alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, shimmer, verse
response_format	string	mp3	Audio format: mp3, opus, aac, flac, wav, pcm
speed	float	1.0	Speed multiplier (0.25–4.0)

Example

curl -X POST https://your-tie-host/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKEN" \
  -d '{
    "model": "gpt-4o-mini-tts",
    "input": "Great job logging your meals today! You hit your protein target.",
    "voice": "nova"
  }' \
  --output response.mp3

Response

Raw audio bytes in the requested format. The Content-Type header reflects the format (e.g. audio/mpeg for mp3).

AI SDK Integration

import { createOpenAI } from "@ai-sdk/openai";
import { experimental_generateSpeech as generateSpeech } from "ai";

const tie = createOpenAI({
  baseURL: "https://your-tie-host/v1",
  apiKey: "your-bearer-token",
});

const result = await generateSpeech({
  model: tie.speech("gpt-4o-mini-tts"),
  text: "Great job logging your meals today!",
  voice: "nova",
});

// result.audio is a Uint8Array of audio bytes

---

Common Pattern: Voice Chat

A typical voice-enabled chat flow combines both endpoints:

1. User speaks → record audio on the client
2. Transcribe → POST /v1/audio/transcriptions → get text
3. Chat → POST /v1/chat/completions with the transcribed text → get AI response
4. Speak → POST /v1/audio/speech with the AI response text → play audio

sequenceDiagram
    participant User
    participant Client
    participant TIE

    User->>Client: Speaks
    Client->>TIE: POST /v1/audio/transcriptions (audio file)
    TIE-->>Client: { "text": "..." }
    Client->>TIE: POST /v1/chat/completions (transcribed text)
    TIE-->>Client: AI response text
    Client->>TIE: POST /v1/audio/speech (response text)
    TIE-->>Client: Audio bytes
    Client->>User: Plays audio

Steps 3 and 4 can overlap — start TTS as soon as the chat response text is available, rather than waiting for the full response.

Models

Transcription

Model	Description
whisper-1	OpenAI Whisper — general-purpose, supports 50+ languages

Text-to-Speech

Model	Description
gpt-4o-mini-tts	Latest, most natural-sounding. Default.
tts-1	Optimized for low latency
tts-1-hd	Optimized for quality

Voices

Voice	Tone
alloy	Neutral, balanced
ash	Warm, conversational
ballad	Soft, expressive
coral	Clear, friendly
echo	Steady, authoritative
fable	Expressive, storytelling
nova	Warm, engaging
onyx	Deep, rich
sage	Calm, measured
shimmer	Bright, upbeat
verse	Versatile, adaptive