AWS Marketplace (SageMaker)
Murf Finch is available on AWS Marketplace as an Amazon SageMaker model package. You subscribe with your AWS account, deploy an endpoint in that account, and call it directly. There is no Murf API key, and no Murf server is in the request path. The container runs with SageMaker network isolation, so audio and transcripts never leave your endpoint. AWS bills you and pays Murf.
The listing has two versions. Finch Global transcribes English and six European languages. Finch Indic transcribes 11 Indian languages plus English (India), and returns word timestamps. Pick the version when you copy the model package ARN. The ARN is different for every version and every Region.
This listing is speech to text only. Text to speech is a separate product: Falcon 2.1 on AWS Marketplace. The hosted Speech to Text API is separate from this page: stream live audio over a WebSocket, or upload a file. Both use a Murf API key. This endpoint uses the SageMaker runtime, and its fields are the ones on this page. A SageMaker batch job is not the hosted file API.
Versions
Each version transcribes only its own languages. Omit the language option and Finch detects the language from the audio. A language code from the other version returns HTTP 400.
Ways to call the endpoint
Prerequisites
-
Subscribe.
AWSMarketplaceManageSubscriptions, or theaws-marketplace:ViewSubscriptions,Subscribe, andUnsubscribeactions. Nothing is charged until an endpoint or a batch job runs. -
Deploy.
AmazonSageMakerFullAccesson a SageMaker execution role. SageMaker Studio and notebook instances already have a role you can use. To create one: -
GPU quota. In Service Quotas → Amazon SageMaker, set
ml.g5.2xlarge for endpoint usageto at least 1. For batch transform,ml.g6.2xlarge for transform job usageis often 0 until you request it. Quota increases can take a day or more. -
Live streaming from Python. Python 3.12+ and
aws-sdk-sagemaker-runtime-http2[awscrt]>=0.11. boto3 does not support the bidirectional API.
Quickstart
About 15 minutes, most of it waiting for the endpoint to start. The notebook does the same steps. It reads an ARN for the notebook’s Region from model_packages.json when that Region is listed there. For any other Region, or to pin a version, paste the ARN from the listing into MODEL_PACKAGE_ARN.
Subscribe and copy the ARN
Open the listing, choose Continue to subscribe, review pricing and the EULA, then Accept offer. Choose Continue to configuration, pick Finch Global or Finch Indic and your Region, and copy the product ARN.
Already subscribed? AWS Marketplace → Manage subscriptions → Murf Finch → Launch new configuration, select the version and Region, and copy the ARN.
Deploy the endpoint
Network isolation is required for Marketplace model packages. The startup health check needs 900 seconds because the model takes a few minutes to load. Least-outstanding-requests routing sends each new stream to the least busy instance once you run more than one.
The endpoint is ready in about 8–10 minutes. describe_model_package and create_model fail when the account is not subscribed to that version.
Transcribe a file
The body is the audio file. samples/en_us_sample.wav is an English clip for Finch Global, and samples/hi_in_sample.wav is Hindi for Finch Indic. Both are from the FLEURS dataset (CC BY 4.0).
Or from a terminal, with the endpoint name in NAME:
Delete the endpoint when you are done
You pay AWS for the GPU instance while the endpoint exists, whether or not you send requests. Delete test endpoints when you finish.
The subscription stays active, so you can deploy again later. To end it, delete your models first, then cancel under AWS Marketplace → Manage subscriptions.
Transcribe a file
InvokeEndpoint returns the full transcript. WAV, FLAC, MP3, OGG/Opus, M4A, and other common formats are accepted. A request can be up to 25 MB (about 13 minutes of 16 kHz WAV, and longer for MP3 or Opus) and must finish within SageMaker’s 60-second limit. Longer files use batch transform.
Content-Type is audio/wav, audio/mpeg, application/octet-stream, or the type that matches the file.
Options go in the X-Amzn-SageMaker-Custom-Attributes header (CustomAttributes in boto3, --custom-attributes in the CLI) as comma-separated key=value pairs. They are not fields in a JSON body.
Response
Every response includes these fields:
A Finch Indic word looks like this:
Stream live audio
Open a bidirectional stream with InvokeEndpointWithBidirectionalStream. examples/stream.py is a complete Python client. It uses AWSCRTHTTPClient against the runtime endpoint on port 8443. Another transport raises UnsupportedTransportError.
--language de sets the language, --bvc suppresses background voices, and --raw prints every message.
Options go in ModelQueryString, for example language=hi&keywords=Murf,Finch. Names here differ from a file request: the query uses language and keywords. The file header uses language_code and keyterms.
You send:
-
Optionally, one JSON text message describing the audio. Without it the endpoint expects 16-bit little-endian mono PCM at 16 kHz.
codecispcm_s16le,mulaw,alaw, oropus(one packet per frame).sample_rateis 8000, 12000, 16000, 24000, 32000, 44100, or 48000. -
Audio as binary frames, ideally 20–100 ms each, at real-time pace.
-
Control messages as JSON text.
Finalizeends the current turn and keeps the stream open.CloseStreamflushes and closes.KeepAliveholds a paused stream open; send it instead of silence.
You receive JSON text messages:
partialupdates the current turn as the speaker talks. Show it as live captions.- One
finalper turn carries the settled text. Afinalwith an empty transcript means the turn contained no speech. rawEventadds timing in seconds from the start of the stream, the detected language, and, on Finch Indic, word timestamps.- The transcript field on a stream is
transcript. A file response usestext. - Errors arrive as a message with
"type": "Error"and amessagestring.
A stream closes after 10 seconds without a first message, or after 180 seconds without audio or KeepAlive.
Batch transform
Put one audio file per S3 object under an input prefix. Each output object is the input name plus .out and holds the same JSON as a real-time response. Files can be up to one hour long.
SplitType None keeps each object as one audio file. Batch transform runs on ml.g6.2xlarge, ml.g6.xlarge, and ml.g5.xlarge, and needs “for transform job usage” quota for that type. The notebook uploads the sample clips and prints each transcript.
Instances and performance
Measured on Amazon SageMaker in us-east-2 in November 2026. Live 16 kHz streams of FLEURS speech were sent at real-time pace, 120 seconds per load level. “Streams” is the highest load tested at which 90% of final transcripts arrived within 250 ms of the end of speech. The stream counts are for Finch Global. Finch Indic stayed under 165 ms (p90) at 64 streams on every instance below. A single stream is 45–85 ms (p90) on all of them.
On one ml.g5.2xlarge, p90 final latency is 66 ms at 1 stream, 106 ms at 32, 150 ms at 64, and 222 ms at 96.
Size the endpoint as peak concurrent streams divided by streams per instance, rounded up, plus one instance for redundancy. For variable traffic, add SageMaker auto scaling on ConcurrentRequestsPerModel.
Other instance types are not supported in this version. ml.g4dn is too slow for live use, and ml.g7e does not start.
When a GPU type is unavailable in an Availability Zone, give the endpoint a fallback list with instance pools. Replace InstanceType in the production variant with:
Every type in the pool needs quota of at least 1.
Accuracy
Word error rate on the FLEURS test sets, with text normalized before scoring:
Accuracy is lower on noisy, overlapping, or far-field speech. Test with your own audio.
Limitations
- Speaker diarization is not included.
- Finch Global returns lowercase text without punctuation, and its
wordsarray is empty. - Each version transcribes only the languages in the versions table.
Pricing
Real-time and streaming usage is billed per minute of audio, in fractions of a minute. Streams of PCM, mu-law, or A-law are billed by the audio duration sent. Opus streams are billed by session time. Pauses covered by KeepAlive are not billed for PCM streams. For a file request, audio_duration_secs is the billed duration.
Batch transform is billed per instance-hour while the job runs. AWS separately bills the SageMaker instance hours. Current prices are on the listing.
Troubleshooting
Security and privacy
- Audio and transcripts stay in your account. With network isolation, the container has no network access and sends nothing to Murf or any third party.
- Audio and transcripts are not used to train models.
- The endpoint writes one line per request to CloudWatch Logs with status and timing. Audio and transcript text are never logged.
Support
Murf cannot see your requests, audio, or transcripts. Email support@murf.ai with the AWS Region, instance type, listing version, the transcription_id or session_id, and the error message. Billing disputes go through AWS Marketplace.