API guide
Speech API
Capability catalogue · ASR contract · TTS contract
Available to invited organizations · 2 November 2026
Use your existing tokenflow API key for transcription and speech synthesis. Check GET /v1/models for the models currently available to your organization.
Speech to text
sensevoice-small accepts WAV audio up to 30 seconds: 16-bit PCM or 32-bit float, one or two channels, 8–48 kHz. Convert MP3 or other formats to WAV first.
curl --fail-with-body https://api.tokenflow.dev/v1/audio/transcriptions \
-H "Authorization: Bearer $TOKENFLOW_API_KEY" \
-F model=sensevoice-small \
-F file=@sample.wav \
-F response_format=verbose_json
Response formats: json, verbose_json or text. Successful requests use at least 10 billed seconds. Reference price: $0.054 per billed audio hour; customer agreements govern payment.
To try it without code, open the transcription playground in the console: record from your microphone or choose a file; it uses your organization’s quota.
Text to speech
tokenflow-tts-1 accepts up to 4,000 characters per request and returns an MP3 file by default. Long text is split into sentences and spoken in one consistent voice; the file starts arriving within seconds and finishes as it is made, so for more than a minute of audio we suggest stream: true. speed takes 0.75 to 1.5 (default 1) for every voice and format; the pitch stays the same, and a clip is billed by its length before the speed change. Choose a preset voice or use instructions to describe a voice; do not supply both. Cloning from your own recordings is not available.
curl --fail-with-body https://api.tokenflow.dev/v1/audio/speech \
-H "Authorization: Bearer $TOKENFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tokenflow-tts-1","input":"你好,欢迎使用语音服务。","voice":"zh-female-calm"}' \
--output speech.mp3
Besides the presets, zh-sunwukong is a Sun Wukong voice made from a licensed recording, and ten English female voices are designed from text descriptions (no human recording):
en-female-warm-us: warm, gentle female, USen-female-sweet-us: sweet, playful female, USen-female-mature-us: rich, mature female, USen-female-southern-us: soft drawl female, US Southen-female-bedtime-us: hushed, soft-spoken female, USen-female-soft-uk: calm, soothing female, UKen-female-posh-uk: crisp, elegant female, UK, RPen-female-lilt-ie: lilting, lively female, Irishen-female-bright-au: bright, cheerful female, Australianen-female-mellow-au: low, mellow female, Australian
These shared voices are served by one node, so they can answer 503 voice_unavailable while that node is busy or under maintenance; retry, or fall back to a preset. The first request after a few idle hours may take a few seconds longer.
Set response_format to mp3 (default), opus, aac, flac, wav or pcm, as in OpenAI's speech API; the OpenAI SDKs work with the TokenFlow base URL and key. pcm is raw 24 kHz 16-bit little-endian mono audio.
To hear the voices without writing code, open the speech playground in the console; it uses your organization’s quota.
Streaming uses stream: true with response_format: "pcm" (default) or "opus". Streamed PCM is the same 24 kHz 16-bit audio; the x-sample-rate and x-sample-format response headers say so. Reference price: $1.00 per hour of audio sent to you, billed by the 0.1 s with at least 1 second per request, and held between two-thirds and twice what the text should take to say. A stream you stop is billed for the audio already sent; failed requests and empty audio are free; voice instructions cost nothing.
Quotas and retries
- Default monthly allowance per organization: 36,000 billed ASR seconds and 72,000 billed TTS seconds (20 hours of audio). All keys share it; it resets at the start of each UTC calendar month. Your administrator can change or disable it. Allowances are usage caps, not free-credit promises.
- TTS: four concurrent requests per organization, eight across external organizations.
- ASR: two concurrent requests per organization, three across external organizations.
- For
429 speech_quota_exceeded, do not retry until the quota is raised or reset. Readx-tokenflow-quota-reset. Usage accounting may lag by about a minute. - For
429 concurrency_limit_exceeded,429 speech_rate_limitedor temporary503responses, respectRetry-Afterand use backoff. Failed requests are not billed.
Long-form speaker-separated transcription and the slow batch TTS model are not offered externally in this release.
Disclosure and data
Tell listeners the voice is AI-generated and preserve the origin metadata: every audio response carries it in the x-aigc-label header, and MP3, AAC, Opus, FLAC and WAV files carry it inside the file. Raw PCM has no file metadata: keep the header’s label and add it when saving or distributing the audio. See the speech terms and speech data policy for use restrictions, voice-description retention and logging.