Dictate a short clip into text for an agent or editor
Four or more companies' docs show a full fit.
What counts as done
Clean punctuated text back for a 30-second clip.
Measured, for our own tests: the text arrives within 2 seconds of the clip ending, with no filler text or hallucinated sentence on a clip that is partly silent. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: transcribe this 20-second voice note
, I'll speak my prompt, type it for me
, turn this voice message into text
Does the job 9
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| Azure AI Speech speech-to-text BB Microsoft Corporation | Fast transcription returns the text synchronously for short files; real-time recognize-once is the SDK path. No silence fixture was run. source |
| Deepgram Speech-to-Text (Nova-3, Flux) BB Deepgram, Inc. | Pre-recorded is synchronous over HTTP and returns the transcript in the response; Pipecat puts Nova-3 finals at 247 ms. No silence fixture was run. source |
| Inworld STT C Theai, Inc. dba Inworld AI | Synchronous POST transcribe returns the transcript for requests to 16 MiB; no silence fixture was run. source |
| MiniMax Speech-to-Text D Nanonoble Pte. Ltd. | Synchronous transcription of clips to 500 seconds with a language header; the guide claims tuning against hallucination, which is a vendor claim. source |
| Mistral Voxtral Transcribe B Mistral AI (RCS Paris 952 418 325) | Synchronous /v1/audio/transcriptions returns the text; acc-09 reports no hallucination on silence for daily use. source |
| Nemotron 3.5 ASR Streaming 0.6B C NVIDIA Corporation | A 0.6B model running faster than real time on a small GPU or laptop via Transformers pipeline or NeMo-Speech.cpp; silence behaviour is undocumented. source |
| OpenAI Speech to Text BB OpenAI OpCo, LLC | Synchronous /v1/audio/transcriptions with gpt-transcribe returns the text; no silence fixture was run and acc-15 used an LLM pass to fix Whisper hallucinations. source |
| Parakeet TDT 0.6B v3 B NVIDIA Corporation | acc-17 reports near-instant local dictation on a MacBook; Transformers 5.10 pipeline runs it. Silence behaviour undocumented. source |
| Smallest.ai Pulse STT B Smallest, Inc. | POST /waves/v1/stt/ is synchronous without webhook_url and returns the transcript; silence behaviour untested. source |
Does the job, with a limit 19
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Amazon Transcribe BB Amazon Web Services, Inc. | Batch jobs are asynchronous with S3 input and polling, so a 30-second clip is not back within 2 seconds; streaming works but the median final latency is 1,136 ms. source |
| AssemblyAI Speech-to-Text (Universal) B AssemblyAI, Inc. | Pre-recorded is an asynchronous job with polling and a 403 rate limit; the streaming path returns finals in about 300 ms but needs a WebSocket. Silence behaviour untested. source |
| Cartesia Ink B Cartesia AI, Inc. | Batch ink-whisper returns a transcript synchronously; realtime finals arrive in about 300 ms. Silence behaviour untested, and realtime bills silence. source |
| Cohere Transcribe 03-2026 C Cohere Inc. | A 2B model transcribes a clip quickly on a GPU, but the blog says it is eager to transcribe non-speech sounds, so a partly silent clip needs a VAD in front. source |
| ElevenLabs Scribe Speech to Text API BB Eleven Labs Inc. | POST /v1/speech-to-text is synchronous and takes clips from 100 ms, but a request under one credit bills one credit and no silence fixture was run. source |
| Giggy Speech to Text E Giggy | Recordings from 0.5 seconds are accepted, but every recorded request is an HTTP 202 then polling, and input must be converted to 16 kHz mono WAV first. source |
| Gladia Speech-to-Text API + MCP BB Gladia SAS | Pre-recorded is an asynchronous job (init, upload, poll or callback), so a 30-second clip is not back within 2 seconds; live sessions suit it better. source |
| Google Cloud Speech-to-Text B Google LLC | Synchronous Recognize takes up to 1 minute or 10 MB and returns directly, but acc-05 saw repeated filler text on noisy or silent audio and a 403 on 20 seconds of silence. source |
| Groq Speech-to-Text BB Groq LLC | Synchronous transcription of a short file is fast on Groq, but every request bills at least 10 seconds and verbose_json exposes no_speech_prob rather than suppressing silence. source |
| IBM Watson Speech to Text C International Business Machines Corporation | Synchronous /v1/recognize returns text for a short clip, but the 30-second inactivity timeout and no silence fixture leave the silence case unchecked. source |
| Ming-3.0-asr-tiny C inclusionAI, Ant Group (named in the site footer of inclusion-ai.org; the LICENSE copyright line reads inclusionAI) | A short clip transcribes in one pass on a CUDA GPU, but the model needs 17.7 GB of BF16 weights and no silence behaviour is documented. source |
| Ming-3.0-audio-tiny D inclusionAI (Ant Group) | A clip transcribes on one GPU with about 25 GB free, but loading runs repository code and silence behaviour is undocumented. source |
| Qwen3-ASR-0.6B C Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check) | Fast on a small GPU through vLLM, but acc-25 reports noise returned as filler interjections and heavy repetition on non-speech sound. source |
| Qwen3-ASR-1.7B B Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check) | Fast on a small GPU through vLLM, but acc-25 reports noise returned as filler interjections and heavy repetition on non-speech sound. source |
| Rev AI Speech-to-Text API C Rev.com, Inc. | Async jobs poll or call back, so a 30-second clip is not back within 2 seconds, and every job bills at least 15 seconds. source |
| Soniox Speech-to-Text B Soniox Inc. | The async API is a job with upload and polling; the realtime socket returns finals in about 266 ms but needs a stream. Silence behaviour untested. source |
| Speechmatics Speech-to-Text BB Cantab Research Ltd | Batch is a job with polling (5-second default wait) or notifications, so a clip is not back within 2 seconds; realtime finals arrive in 369 to 495 ms. source |
| Underdog Bark 3.0 E Conway Research | About 1.5 seconds per minute of audio on an M2 per the card, but every route runs Conway's Python and the first run needs the network and about 6 GB to extract. source |
| Voxtral Mini 4B Realtime 2602 B Mistral AI (RCS Paris 952 418 325) | Runs on a 16 GB GPU in vLLM or as a Q4 GGUF in llama.cpp, but output is plain text and silence behaviour is undocumented. source |
Doesn't do this job 1
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Ming-3.0-audio-flash E inclusionAI, Ant Group (named in the inclusion-ai.org footer; no registered company named) | Needs a multi-GPU server (259 GB BF16), so not a path for a waiting user on a laptop or one GPU. |
3 listings in the category were added after this reading and aren't marked yet.
What stops agents finishing
- every request billed as at least 10 seconds (Groq), so many short clips cost more than their length
- tool must have 16 kHz mono WAV and nothing else (Giggy)
- noise or breath transcribed as filler words (acc-25)
Around it
Before: voice.capture-microphone. After: llm.prompt, editor.insert-text.
Where this comes from
Weight 10 of 100 in Speech-to-text: 4 of 32 accounts (acc-05, acc-17, acc-18, acc-25); heavily represented in Hacker News dictation-app threads, where local models dominate
The same as data: /api/v1/use-cases/speech-to-text.dictation-to-agent.json, or the MCP tool get_use_case with id speech-to-text.dictation-to-agent. Other jobs in this category: /api/v1/niches?category=speech-to-text.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.