> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://murf.ai/api/docs/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://murf.ai/api/docs/_mcp/server.

# Speech to Text (Beta)

> Murf Speech to Text streams audio over a WebSocket and returns partial and final transcripts with word-level timestamps, built for voice agents and telephony.

Murf Speech to Text (STT) converts live audio into text in real time. You stream audio over a WebSocket and receive `partial` transcripts while the caller is speaking, then a `final` transcript with word-level timestamps when you end the turn. It is built for voice agents, IVR, and call analytics, and accepts telephony audio (8 kHz µ-law and A-law) directly.

> **Warning**
>
> Speech to Text (Beta) is available in the **India** region only. Connect to `wss://in.api.murf.ai/v1/transcription/stream-input`.

Combined with [Falcon 2.1](/api/docs/text-to-speech-models/falcon-2-1), Murf now covers both ends of a voice agent: hearing the caller and speaking back.

## Ideal for

* **Voice agents and IVR**: Show the caller's words as they speak, and pass each completed turn to your LLM. When your agent decides the caller has finished speaking, send `{"type": "Finalize"}` (see [Ending a turn with Finalize](/api/docs/speech-to-text/streaming#ending-a-turn-with-finalize)) to get that turn's `final` transcript immediately.
* **Collections and payment reminders**: Boost recognition of product names and account terms with [keyword boosting](/api/docs/speech-to-text/keyword-boosting).
* **Customer support**: Transcribe calls in the caller's own language, or detect it automatically.
* **Call analytics and QA**: Get word-level timestamps on each `final` transcript for search, redaction, and review.

## Key features

#### Real-time streaming

Stream audio over one WebSocket. `partial` transcripts update while the caller speaks, and a `final` transcript arrives when the turn ends.

#### 12 languages + auto-detect

English (India), Hindi, Assamese, Bengali, Gujarati, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil and Telugu, or let the model detect the language.

#### Telephony-ready audio

Send 8 kHz µ-law or A-law straight from your telephony provider, plus PCM and Opus at rates up to 48 kHz.

#### Keyword boosting

Improve recognition of brand names, product terms and domain vocabulary per connection.

#### Multi-turn sessions

Keep one connection open for a whole call. End each turn with `Finalize`; timestamps stay on one session timeline.

#### Word-level timestamps

Every `final` transcript includes start and end times for each word.

## How it works

#### Connect

Open a WebSocket to `wss://in.api.murf.ai/v1/transcription/stream-input` with your API key in the `api_key` query parameter, and optionally `language` and `keywords`.

#### Stream audio

Send audio as binary frames. The server detects speech and returns `partial` messages as the turn grows. The default format is 16-bit PCM, 16 kHz, mono; for telephony or other formats, see [Audio formats](/api/docs/speech-to-text/audio-formats).

#### End turns and the session

Send `{"type": "Finalize"}` to end a turn and get its `final` transcript immediately. Send `{"type": "CloseStream"}` when the call ends.

## Coming soon

The following query parameters are accepted on the connection URL but have no effect yet:

* **`commit_mode=auto`**: ends a turn automatically when the caller stops speaking. Until it is available, a turn ends only when you send `Finalize`.
* **`bvc=true`**: removes background voices before transcription.

## Pricing

Speech to Text costs **\$0.24 per hour** of audio, billed per second. Enterprise customers can get custom pricing; [contact sales](https://murf.ai/enterprise?src=d_contact_sales_api_docs).

[See Pricing](https://murf.ai/pricing?product=api)

## Get started

#### [Streaming](/api/docs/speech-to-text/streaming)

Transcribe a file or your microphone in a few minutes.

#### [API reference](/api/docs/api-reference/speech-to-text/stream-input)

Every message, field and close code.

#### [Audio formats](/api/docs/speech-to-text/audio-formats)

Codecs, sample rates and telephony examples.

#### [Languages](/api/docs/speech-to-text/languages)

Supported languages and automatic detection.