---
title: "Create transcription (LiteLLM - OpenAI Whisper)"
method: POST
path: "/litellm/v1/audio/transcriptions"
tags: ["LiteLLM Integration"]
---

# Create transcription (LiteLLM - OpenAI Whisper)

`POST /litellm/v1/audio/transcriptions`

Transcribes audio into text using OpenAI Whisper via LiteLLM.

## Response `200`

Successful response

- TranscriptionResponse
  - `duration` number
  - `language` string
  - `logprobs` object[]
    - `bytes` integer[]
    - `logprob` number
    - `token` string
  - `segments` object[]
    - `id` integer
    - `seek` integer
    - `start` number
    - `end` number
    - `text` string
    - `tokens` integer[]
    - `temperature` number
    - `avg_logprob` number
    - `compression_ratio` number
    - `no_speech_prob` number
  - `task` string
  - `text` string
  - `usage` object
    - `type` 'tokens' | 'duration'
    - `input_tokens` integer
    - `input_token_details` object
      - `text_tokens` integer
      - `audio_tokens` integer
    - `output_tokens` integer
    - `total_tokens` integer
    - `seconds` integer
  - `words` object[]
    - `word` string
    - `start` number
    - `end` number
  - `extra_fields` BifrostResponseExtraFields — Additional fields included in responses
    - `request_type` string — Type of request that was made
    - `provider` 'openai' | 'azure' | 'anthropic' | 'bedrock' | 'cohere' | 'vertex' | 'vllm' | 'mistral' | 'ollama' | 'groq' | 'sgl' | 'parasail' | 'perplexity' | 'replicate' | 'cerebras' | 'deepseek' | 'gemini' | 'openrouter' | 'elevenlabs' | 'huggingface' | 'nebius' | 'xai' | 'runway' | 'fireworks' — AI model provider identifier
    - `model_requested` string — The model that was requested
    - `model_deployment` string — The actual model deployment used
    - `latency` integer — Request latency in milliseconds
    - `chunk_index` integer — Index of the chunk for streaming responses
    - `raw_request` object — Raw request if enabled
    - `raw_response` object — Raw response if enabled
    - `cache_debug` BifrostCacheDebug
      - `cache_hit` boolean
      - `cache_id` string
      - `hit_type` string
      - `requested_provider` string
      - `requested_model` string
      - `provider_used` string
      - `model_used` string
      - `input_tokens` integer
      - `threshold` number
      - `similarity` number

## Other responses

- `400` — Bad request
- `500` — Internal server error

---

[API](https://skmtc.net/getbifrost/apis/bifrost-api.md) · [All operations](https://skmtc.net/getbifrost/apis/bifrost-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/getbifrost/bifrost-api/versions/f8cab88f64ea/schema)