ASR API

sensevoice-small

Transcribe short WAV recordings to text.

InputUp to 30 seconds · WAV
Pricing$0.054 / audio hour
Default organization cap10 billed hours / month

Try it in the console playground — you sign in first, and it uses your organization’s quota.

Quickstart

Set TOKENFLOW_API_KEY privately in your shell. This page never asks for your key or runs a request.

Save a supported WAV as sample.wav in your current directory. The command uploads that file.

Transcription

POST /v1/audio/transcriptions · multipart/form-data

curl · uploads sample.wav
curl --fail-with-body 'https://api.tokenflow.dev/v1/audio/transcriptions' \
  -H "Authorization: Bearer $TOKENFLOW_API_KEY" \
  --form-string 'model=sensevoice-small' \
  -F 'file=@sample.wav' \
  --form-string 'response_format=verbose_json'

  • Upload a non-empty WAV: PCM16 or float32, 1–2 channels, 8–48 kHz.
  • The file example names a local upload; do not send that name as a text form field.

Parameters & limits

Audio length
Up to 30 seconds per request
File format
WAV: 16-bit PCM or 32-bit float
Channels & sample rate
Mono or stereo · 8–48 kHz
Request size
25 MiB
Speaker separation
Not supported; use this model for short transcription

Read the speech guide →

Pricing & usage

$0.054 / audio hour

Successful requests are billed for at least 10 seconds each. Short clips still use this minimum.

Default monthly cap
10 billed hours / month
Concurrent requests
2 per organization; 3 across external organizations

All keys share the organization’s UTC-month allowance. An administrator can change it. These are default caps, not your remaining quota or free credits.

Reference price checked 2026-11-18. Your customer agreement governs settlement.

Quota errors and retry guidance →

View the machine-readable contract

Published specification only. Inspect the discovery API for runtime observations; discovery does not reserve capacity.

{
  "id": "sensevoice-small",
  "kind": "asr",
  "summary": "Transcribe short WAV recordings to text.",
  "tags": [
    "audio",
    "transcription",
    "语音识别",
    "转写"
  ],
  "protocols": [
    {
      "id": "transcription",
      "method": "POST",
      "path": "/v1/audio/transcriptions",
      "content_type": "multipart/form-data",
      "modes": [
        "json",
        "verbose_json",
        "text"
      ],
      "schema_scope": "complete_fields",
      "input_schema": {
        "type": "object",
        "properties": {
          "model": {
            "const": "sensevoice-small"
          },
          "file": {
            "type": "string",
            "format": "binary"
          },
          "language": {
            "type": "string",
            "maxLength": 16
          },
          "response_format": {
            "enum": [
              "json",
              "verbose_json",
              "text"
            ]
          },
          "temperature": {
            "description": "Accepted and ignored by the engine."
          }
        },
        "required": [
          "model",
          "file"
        ],
        "additionalProperties": false
      },
      "constraints": [
        "Upload a non-empty WAV: PCM16 or float32, 1–2 channels, 8–48 kHz.",
        "The file example names a local upload; do not send that name as a text form field."
      ],
      "example": {
        "model": "sensevoice-small",
        "file": "@sample.wav",
        "response_format": "verbose_json"
      }
    }
  ],
  "guaranteed": {
    "max_audio_ms": 30000,
    "max_request_bytes": 26214400,
    "encodings": [
      "pcm16",
      "float32"
    ],
    "channels": [
      1,
      2
    ],
    "sample_rate_hz": [
      8000,
      48000
    ]
  },
  "documented": {
    "guide": "https://tokenflow.dev/speech",
    "limits": [
      "No speaker diarization; convert other formats to WAV first."
    ]
  },
  "billing": {
    "meter": "audio_ms",
    "minimum_billed_units": 10000,
    "measured": "audio_duration_ms",
    "pricing": {
      "meter": "audio_ms",
      "usd_per_hour": 0.054,
      "unit": "audio_hour",
      "status": "open",
      "currency": "USD",
      "checked_at": "2026-11-18",
      "settlement": "customer_agreement"
    }
  },
  "external_limits": {
    "concurrency": {
      "perTenant": 2,
      "external": 3,
      "retryAfterS": 2
    },
    "default_monthly": {
      "limit": 36000000,
      "unit": "audio_ms"
    },
    "quota_is_not_free_credit": true
  },
  "schema_version": 1,
  "publication": "public",
  "next": [
    {
      "method": "POST",
      "path": "/v1/audio/transcriptions",
      "content_type": "multipart/form-data",
      "body": {
        "model": "sensevoice-small",
        "file": "@sample.wav",
        "response_format": "verbose_json"
      }
    }
  ]
}

For developers and agents

Choose your way in

Human guides and machine-readable contracts describe the same APIs.

Need runtime observations? Use the public discovery API. Tenant access and quotas require your API key.

Published contract updated 2 November 2026. Terms · Data policy · All capabilities