GPT Transcribe API: Endpoint & Pricing
GPT Transcribe brings speech-to-text speech-to-text to LLM.API for voice notes, calls, and caption pipelines.
What is GPT Transcribe?
GPT Transcribe is a speech-to-text model on LLM.API (`gpt-transcribe`). Speech-to-text model by Azure. Feed audio and receive text transcripts for captions, agents, and searchable archives.
Can you self-host GPT Transcribe?
No. We found no public weights for GPT Transcribe on Hugging Face, so there is nothing to download, quantize or serve on your own GPUs: no VRAM budget, no vLLM or GGUF build to plan for. The only way to run it is over an API.
Skip the deploy — use LLM.API as your endpoint
No GPUs, no quantization trade-offs. Same model, OpenAI-compatible, up to 30% below list price.
Providers
LLM.API routes GPT Transcribe to the providers below, with discounted effective rates versus list price.
List price by provider
InputOutputProvider list prices; the LLM.API discount applies on top.
| Provider | Pricing | Context | Capabilities |
|---|---|---|---|
| in $0; out — per minute of audio | 128K tokens | — |
Prices and availability from the LLMAPI catalogue, updated nightly. Last updated 8 Oct 2026.
Try this model
Test GPT Transcribe right here — free to start.
Suggestions for your first prompt
Code snippet
Call GPT Transcribe through the OpenAI-compatible API — STT via LLM.API (see docs for audio endpoints).
Switching from OpenAI? Change 2 lines.
- base_url="https://api.openai.com/v1"
- api_key="YOUR_OPENAI_KEY"
+ base_url="https://api.llmapi.ai/v1"
+ api_key="YOUR_LLMAPI_KEY"Everything else stays the same — SDK, message format, tools, streaming. Set model to gpt-transcribe and the call runs unchanged.
curl https://api.llmapi.ai/v1/chat/completions \
-H "Authorization: Bearer $LLMAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-transcribe",
"messages": [
{"role": "user", "content": "Give me three crisp launch checklist items."}
]
}'from openai import OpenAI
client = OpenAI(
api_key="YOUR_LLMAPI_KEY",
base_url="https://api.llmapi.ai/v1",
)
resp = client.chat.completions.create(
model="gpt-transcribe",
messages=[
{"role": "system", "content": "You are a precise product assistant."},
{"role": "user", "content": "Give me three crisp launch checklist items."},
],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.LLMAPI_KEY,
baseURL: "https://api.llmapi.ai/v1",
});
const resp = await client.chat.completions.create({
model: "gpt-transcribe",
messages: [
{ role: "user", content: "Give me three crisp launch checklist items." },
],
});
console.log(resp.choices[0].message.content);stream = client.chat.completions.create(
model="gpt-transcribe",
messages=[{"role": "user", "content": "Write a haiku about latency."}],
stream=True,
)
for chunk in stream:
delta = chunk.choices[0].delta.content
if delta:
print(delta, end="", flush=True){
"model": "gpt-transcribe",
"messages": [
{"role": "system", "content": "You are a precise product assistant."},
{"role": "user", "content": "Give me three crisp launch checklist items."}
]
}ENDPOINTS
Supported endpoints & features
Base URL https://api.llmapi.ai/v1 · model ID gpt-transcribe · OpenAI-compatible.
POST /v1/chat/completionsChat Completions — supported
| Feature | Status | How to set it |
|---|---|---|
| Function calling (tools) | Not supported | tools, tool_choice |
| Parallel tool calls | Not supported | parallel_tool_calls |
| JSON mode | Not supported | response_format: {"type": "json_object"} |
| Structured outputs | Not supported | response_format: {"type": "json_schema", …} |
| Streaming | Not supported | stream: true |
| Vision (image input) | Not supported | image_url content parts |
| Web search | Not supported | web_search |
ERRORS
Errors & fallback routing
| Code | What it means | What to do |
|---|---|---|
401 | Missing or invalid API key. | Send Authorization: Bearer YOUR_LLMAPI_KEY and check the key is active. |
429 | Rate limited, or the upstream provider is throttling the request. | Back off and retry with jitter; the gateway also retries the request on another provider where one is available. |
5xx | Upstream provider error or timeout. | Retry; fallback routing sends the retry to the next healthy provider for this model. |
When a provider fails or throttles, the request is routed to the next provider serving this model — the ones listed in the providers table above.
GPT Transcribe in production
What the model is good at.
Streaming recognition
Supports low-latency partial transcripts when the provider offers streaming STT. Reflects speech-to-text positioning for this endpoint.
Caption generation
Produces base transcripts for subtitle workflows. Grounded in the model's stt role rather than generic chat claims.
Multilingual audio
Handles diverse accents and languages depending on the model. Relevant for `gpt-transcribe` workloads on LLM.API.
Speech transcription
Converts spoken audio into text for captions, notes, and search. Grounded in the model's stt role rather than generic chat claims.
Meeting capture
Fits voice notes, calls, and meeting recording pipelines. Relevant for `gpt-transcribe` workloads on LLM.API.
What you get when you call GPT Transcribe through LLM.API.
Unified AI Routing
Reach GPT Transcribe and sibling models through one OpenAI-compatible endpoint.
One endpoint, every model.Cost Control
Production: Compare provider price points and keep spend visible as you scale GPT Transcribe.
More performance, less spend.Reliability Layer
Production: Retry and route across configured providers when a single upstream blips.
Never go dark on users.Observability
Practical: Trace prompts, tokens, and errors for GPT Transcribe alongside the rest of your stack.
See every token, everywhere.Drop-in SDKs
Keep using familiar OpenAI client patterns with base URL https://api.llmapi.ai/v1.
Think tasks, not models.Model Breadth
Production: Swap GPT Transcribe for chat, media, or embedding alternatives without rewriting auth.
Scale from 1 to millions.
When to Use — When NOT to Use
Use it if...
- You need speech-to-text for batch or streaming audio (GPT Transcribe)
- You will pipe transcripts into search or LLM summarization (GPT Transcribe)
- Voice is a primary input modality in your product (GPT Transcribe)
Avoid if...
- You need text-to-speech or chat generation instead of transcription
- Your audio cannot leave your compliance boundary and you lack an approved provider path
- You require guaranteed perfect transcripts for every accent without evaluation
COMMUNITY
What developers say about speech-to-text models
Summarised from publicly published developer and community reviews of this model family. Opinions are the sources’, not LLM.API’s, and may not be specific to GPT Transcribe.
- Head-to-head tests of the leading APIs land within a point or two of each other; the choice usually comes down to language coverage, streaming latency and batch pricing.
- Voice-agent developers report streaming latency and endpointing quality matter more in production than headline word-error rates.
- Whisper-family models remain the default open baseline, with hosted providers winning on real-time features and diarization.
SOURCES
Frequently Asked Questions
What is the context length for GPT Transcribe?
Reported context for GPT Transcribe is 128K tokens. Always verify the active provider row if multiple providers are listed.
When should I choose GPT Transcribe?
Voice is a primary input modality in your product — especially when you specifically need GPT Transcribe.
Does GPT Transcribe support streaming?
Streaming depends on the active provider; check the providers table on this page for flags.
How is GPT Transcribe priced on LLM.API?
Listed pricing metadata shows: In $4.5 / 1M tokens. LLM.API may offer discounted effective rates (illustrative ~30% callout vs list when available).. Confirm live rates in the LLM.API dashboard or docs before production budgeting.
Is GPT Transcribe a chat model?
No—GPT Transcribe is categorized as a stt model. Use the matching API surface rather than assuming chat completions.
What modalities does GPT Transcribe support?
GPT Transcribe accepts audio and produces text according to its architecture metadata on LLM.API.
What are limitations of GPT Transcribe?
Like other API models, GPT Transcribe can be wrong, incomplete, or uneven on edge cases. Validate outputs for high-stakes use. Media/OCR/STT models additionally depend on input quality.
Which providers serve GPT Transcribe?
LLM.API currently lists: azure. Availability can vary by region and account.
How do I call GPT Transcribe via API?
Send OpenAI-compatible requests to https://api.llmapi.ai/v1 with model "gpt-transcribe" and your LLM.API key. See the code snippet on this page.
Where is the canonical page for GPT Transcribe?
https://llmapi.ai/models/openai-gpt-transcribe/
COMPARE
Competitive Models
ElevenLabs Scribe v2
Input$0.0037 / minuteList price per minute of audio.
$0.0037 in / — out per minute of audio, context varies — the closest current alternative to GPT Transcribe.
AssemblyAI U3 RT Pro
Input$0.0075 / minuteList price per minute of audio.
$0.0075 in / — out per minute of audio, context varies — the closest current alternative to GPT Transcribe.
Deepgram Flux (English)
Input$0.0077 / minuteList price per minute of audio.
$0.0077 in / — out per minute of audio, context varies — the closest current alternative to GPT Transcribe.
Get one key to every model
Swap your API key. Keep your code.